UNIT II

AI TECHNOLOGIES
• An Artificial Neural Network (ANN) is an information processing
paradigm that is inspired by the brain. ANNs, like people, learn by
examples. An ANN is configured for a specific application, such as
pattern recognition or data classification, through a learning
process. Learning largely involves adjustments to the synaptic
connections that exist between the neurons.
• Artificial Neural Networks (ANNs) are a type of machine learning
model that are inspired by the structure and function of the
human brain. They consist of layers of interconnected “neurons”
that process and transmit information.
• There are several different architectures for ANNs, each with their
own strengths and weaknesses. Some of the most common
architectures include:
• Feedforward Neural Networks: This is the simplest type of ANN
architecture, where the information flows in one direction from input to
output. The layers are fully connected, meaning each neuron in a layer
is connected to all the neurons in the next layer.
• Recurrent Neural Networks (RNNs): These networks have a “memory”
component, where information can flow in cycles through the network.
This allows the network to process sequences of data, such as time
series or speech.
• Convolutional Neural Networks (CNNs): These networks are designed
to process data with a grid-like topology, such as images. The layers
consist of convolutional layers, which learn to detect specific features
in the data, and pooling layers, which reduce the spatial dimensions of
the data.
• Autoencoders: These are neural networks that are used for unsupervised
learning. They consist of an encoder that maps the input data to a lower-
dimensional representation and a decoder that maps the representation back to
the original data.
• Generative Adversarial Networks (GANs): These are neural networks that are
used for generative modeling. They consist of two parts: a generator that learns
to generate new data samples, and a discriminator that learns to distinguish
between real and generated data.
• The model of an artificial neural network can be specified by three entities:

• Interconnections
• Activation functions
• Learning rules
• Interconnections:
• Interconnection can be defined as the way processing elements
(Neuron) in ANN are connected to each other. Hence, the arrangements
of these processing elements and geometry of interconnections are very
essential in ANN.
These arrangements always have two layers that are common to all
network architectures, the Input layer and output layer where the input
layer buffers the input signal, and the output layer generates the output
of the network. The third layer is the Hidden layer, in which neurons are
neither kept in the input layer nor in the output layer. These neurons are
hidden from the people who are interfacing with the system and act as a
black box to them. By increasing the hidden layers with neurons, the
system’s computational and processing power can be increased but the
training phenomena of the system get more complex at the same time.
• There exist five basic types of neuron connection architecture :
•
1.Single-layer feed-forward network
2.Multilayer feed-forward network
3.Single node with its own feedback
4.Single-layer recurrent network
5.Multilayer recurrent network
• 1. Single-layer feed-forward network
• In this type of network, we have only two layers input layer and the
output layer but the input layer does not count because no computation
is performed in this layer. The output layer is formed when different
weights are applied to input nodes and the cumulative effect per node is
taken. After this, the neurons collectively give the output layer to
compute the output signals.
•
• 2. Multilayer feed-forward network
• This layer also has a hidden layer that is internal to the network and has
no direct contact with the external layer. The existence of one or more
hidden layers enables the network to be computationally stronger, a
feed-forward network because of information flow through the input
function, and the intermediate computations used to determine the
output Z. There are no feedback connections in which outputs of the
model are fed back into itself.

•
MULTILAYER FEED-FORWARD
NETWORK
• 3. Single node with its own feedback
• When outputs can be directed back as inputs to the same layer or
preceding layer nodes, then it results in feedback networks.
Recurrent networks are feedback networks with closed loops. The
above figure shows a single recurrent network having a single
neuron with feedback to itself.
SINGLE NODE WITH ITS OWN
FEEDBACK
• Single node with its own feedback
• The above network is a single-layer network with a feedback
connection in which the processing element’s output can be
directed back to itself or to another processing element or
both. A recurrent neural network is a class of artificial neural
networks where connections between nodes form a directed
graph along a sequence. This allows it to exhibit dynamic
temporal behavior for a time sequence. Unlike feedforward
neural networks, RNNs can use their internal state (memory) to
process sequences of inputs.
SINGLE NODE WITH ITS OWN
FEEDBACK
• 5. Multilayer recurrent network
• In this type of network, processing element output can be directed to
the processing element in the same layer and in the preceding layer
forming a multilayer recurrent network. They perform the same task for
every element of a sequence, with the output being dependent on the
previous computations. Inputs are not needed at each time step. The
main feature of a Recurrent Neural Network is its hidden state, which
captures some information about a sequence.
•
MULTILAYER RECURRENT NETWORK
IMPLEMENTING ARTIFICIAL NEURAL
NETWORK TRAINING PROCESS IN PYTHON

• An Artificial Neural Network (ANN) is an information

processing paradigm that is inspired the brain. ANNs, like
people, learn by example. An ANN is configured for a specific
application, such as pattern recognition or data classification,
through a learning process. Learning largely involves
adjustments to the synaptic connections that exist between
the neurons.
IMPLEMENTING ARTIFICIAL NEURAL
NETWORK TRAINING PROCESS IN
PYTHON
• The brain consists of hundreds of billions of cells called neurons.
These neurons are connected together by synapses which are
nothing but the connections across which a neuron can send an
impulse to another neuron. When a neuron sends an excitatory
signal to another neuron, then this signal will be added to all of
the other inputs of that neuron. If it exceeds a given threshold
then it will cause the target neuron to fire an action signal
forward — this is how the thinking process works internally.
In Computer Science, we model this process by creating
“networks” on a computer using matrices. These networks can be
understood as an abstraction of neurons without all the biological
complexities taken into account. To keep things simple, we will
just model a simple NN, with two layers capable of solving a
linear classification problem.
• Let’s say we have a problem where we want to predict output given a set
of inputs and outputs as training example like so:
• Note that the output is directly related to the third column i.e. the values
of input 3 is what the output is in every training example in fig. 2. So for
the test example output value should be 1.
• The training process consists of the following steps:
1.Forward Propagation:
Take the inputs, multiply by the weights (just use random numbers as
weights)
Let Y = WiIi = W1I1+W2I2+W3I3
Pass the result through a sigmoid formula to calculate the neuron’s
output. The Sigmoid function is used to normalize the result between 0
and 1:
1/1 + e-y
• Back Propagation
Calculate the error i.e the difference between the actual output and
the expected output. Depending on the error, adjust the weights by
multiplying the error with the input and again with the gradient of the
Sigmoid curve:
Weight += Error Input Output (1-Output) ,here Output (1-Output) is
derivative of sigmoid curve.
• Note: Repeat the whole process for a few thousand iterations.
• Difference between Biological Neurons and Artificial Neurons

Biological Neurons Artificial Neurons

Major components: Axions, Dendrites, Major components: Axions, Dendrites,
Synapse Synapse
The arrangements and connections of the
neurons made up the network and have three
layers. The first layer is called the input layer
Information from other neurons, in the form
and is the only layer exposed to external
of electrical impulses, enters the dendrites at
signals. The input layer transmits signals to
connection points called synapses. The
the neurons in the next layer, which is called
information flows from the dendrites to the
a hidden layer. The hidden layer extracts
cell where it is processed. The output signal,
relevant features or patterns from the
a train of impulses, is then sent down the
received signals. Those features or patterns
axon to the synapse of other neurons.
that are considered important are then
directed to the output layer, which is the final
layer of the network.

A synapse is able to increase or decrease the The artificial signals can be changed by
strength of the connection. This is where weights in a manner similar to the physical
information is stored. changes that occur in the synapses.
 DIFFERENCE BETWEEN THE HUMAN BRAIN AND COMPUTERS IN TERMS OF HOW
INFORMATION IS PROCESSED.

Human Brain(Biological Neuron

Computers(Artificial Neuron Network)
Network)
The human brain works asynchronously Computers(ANN) work synchronously.

Biological Neurons compute slowly (several ms Artificial Neurons compute fast (<1 nanosecond
per computation) per computation)

The brain represents information in a distributed In computer programs every bit has to function
way because neurons are unreliable and could as intended otherwise these programs would
die any time. crash.

Our brain changes their connectivity over time to The connectivity between the electronic
represents new information and requirements components in a computer never change unless
imposed on us. we replace its components.

Biological neural networks have complicated

ANNs are often in a tree structure.
topologies.
• Advantage of Using Artificial Neural Networks
• Problem in ANNs can have instances that are represented by many
attribute-value pairs.
• ANNs used for problems having the target function output may be
discrete-valued, real-valued, or a vector of several real- or discrete-valued
attributes.
• ANN learning methods are quite robust to noise in the training data. The
training examples may contain errors, which do not affect the final output.
• It is used generally used where the fast evaluation of the learned target
function may be required.
• ANNs can bear long training times depending on factors such as the
number of weights in the network, the number of training examples
considered, and the settings of various learning algorithm parameters.
• What is Multi-layer Networks?
• Multi-layer Neural Networks A Multi-Layer Perceptron (MLP) or Multi-
Layer Neural Network contains one or more hidden layers (apart from
one input and one output layer). While a single layer perceptron can
only learn linear functions, a multi-layer perceptron can also learn non –
linear functions.
• This neuron takes as input x1,x2,….,x3 (and a +1 bias term), and
outputs f(summed inputs+bias), where f(.) called the activation
function. The main function of Bias is to provide every node with a
trainable constant value (in addition to the normal inputs that the
node receives). Every activation function (or non-linearity) takes a
single number and performs a certain fixed mathematical operation
on it. There are several activation functions you may encounter in
practice:
• Sigmoid:takes real-valued input and squashes it to range between 0
and 1.
 MATHEMATICALLY UNDERSTANDING NN
• Artificial Neural Networks contain artificial neurons which are called units. These units
are arranged in a series of layers that together constitute the whole Artificial Neural
Network in a system. This article provides the outline for understanding the Artificial
Neural Network.
• Characteristics of Artificial Neural Network
1.It is neuraly implemented mathematical model
2.It contains huge number of interconnected processing elements called neurons to do
all operations
3.Information stored in the neurons are basically the weighted linkage of neurons
4.The input signals arrive at the processing elements through connections and
connecting weights.
5.It has the ability to learn , recall and generalize from the given data by suitable
assignment and adjustment of weights.
6.The collective behavior of the neurons describes its computational power, and no
single neuron carries specific information .
• How Simple Neuron Works ?
• Let there are two neurons X and Y which is transmitting signal to another
neuron Z . Then , X and Y are input neurons for transmitting signals and Z is
output neuron for receiving signal . The input neurons are connected to the
output neuron , over a interconnection links ( A and B) as shown in figure .
• For above neuron architecture, the net input has to be calculated in the way. I =
xA + yB
• where x and y are the activations of the input neurons X and Y. The output z of
the output neuron Z can be obtained by applying activations over the net
input. O = f(I), Output = Function ( net input calculated )
• The function to be applied over the net input is called activation function. There
are various activation function possible for this.
• Application of Neural Network
1.Every new technology need assistance from the previous one i.e. data
from previous ones and these data are analyzed so that every pros and
cons should be studied correctly. All of these things are possible only
through the help of neural network.
2.Neural network is suitable for the research on Animal behavior,
predator/prey relationships and population cycles.
3.It would be easier to do proper valuation of property, buildings,
automobiles, machinery etc. with the help of neural network.
4.Neural Network can be used in betting on horse races, sporting events,
and most importantly in stock market.
5.It can be used to predict the correct judgment for any crime by using a
large data of crime details as input and the resulting sentences as output.
6.By analyzing data and determining which of the data has any fault
( files diverging from peers ) called as Data mining, cleaning and
validation can be achieved through neural network.
7.Neural Network can be used to predict targets with the help of echo
patterns we get from sonar, radar, seismic and magnetic instruments.
8.It can be used efficiently in Employee hiring so that any company can
hire the right employee depending upon the skills the employee has and
what should be its productivity in future.
9.It has a large application in Medical Research.
10.It can be used to for Fraud Detection regarding credit cards ,
insurance or taxes by analyzing the past records .
 DEEP LEARNING
• Deep learning is a method in artificial intelligence
(AI) that teaches computers to process data in a way
that is inspired by the human brain. Deep learning
models can recognize complex patterns in pictures,
text, sounds, and other data to produce accurate
insights and predictions. You can use deep learning
methods to automate tasks that typically require
human intelligence, such as describing images or
transcribing a sound file into text.
DEEP LEARNING

• Deep learning is a subset of machine learning that uses

multilayered neural networks, called deep neural networks,
to simulate the complex decision-making power of the human
brain. Some form of deep learning powers most of the
artificial intelligence (AI) applications in our lives today.
• Why is deep learning important?
• Artificial intelligence (AI) attempts to train computers to think and learn as
humans do. Deep learning technology drives many AI applications used in
everyday products, such as the following:
• Digital assistants
• Voice-activated television remotes
• Fraud detection
• Automatic facial recognition
• It is also a critical component of emerging technologies such as self-driving
cars, virtual reality, and more.
• Deep learning models are computer files that data scientists have trained to
perform tasks using an algorithm or a predefined set of steps. Businesses use
deep learning models to analyze data and make predictions in various
applications.
• How does deep learning work?
• Deep learning algorithms are neural networks that are modeled
after the human brain. For example, a human brain contains
millions of interconnected neurons that work together to learn
and process information. Similarly, deep learning neural
networks, or artificial neural networks, are made of many layers
of artificial neurons that work together inside the computer.
• Artificial neurons are software modules called nodes, which use
mathematical calculations to process data. Artificial neural
networks are deep learning algorithms that use these nodes to
solve complex problems.
• What are the components of a deep learning network?
• The components of a deep neural network are the following.
• Input layer
• An artificial neural network has several nodes that input data into
it. These nodes make up the input layer of the system.
• Hidden layer
• The input layer processes and passes the data to layers further in
the neural network. These hidden layers process information at
different levels, adapting their behavior as they receive new
information. Deep learning networks have hundreds of hidden
layers that they can use to analyze a problem from several
different angles.
• For example, if you were given an image of an unknown animal that you had to
classify, you would compare it with animals you already know. For example,
you would look at the shape of its eyes and ears, its size, the number of legs,
and its fur pattern. You would try to identify patterns, such as the following:
• The animal has hooves, so it could be a cow or deer.
• The animal has cat eyes, so it could be some type of wild cat.
• The hidden layers in deep neural networks work in the same way. If a deep
learning algorithm is trying to classify an animal image, each of its hidden
layers processes a different feature of the animal and tries to accurately
categorize it.
• Output layer
• The output layer consists of the nodes that output the data. Deep learning
models that output "yes" or "no" answers have only two nodes in the output
layer. On the other hand, those that output a wider range of answers have
more nodes.
• What are the benefits of deep learning over machine learning?
• A deep learning network has the following benefits over traditional
machine learning.
• Efficient processing of unstructured data
• Machine learning methods find unstructured data, such as text
documents, challenging to process because the training dataset can
have infinite variations. On the other hand, deep learning models can
comprehend unstructured data and make general observations without
manual feature extraction. For instance, a neural network can recognize
that these two different input sentences have the same meaning:
• Can you tell me how to make the payment?
• How do I transfer money?
• Hidden relationships and pattern discovery
• A deep learning application can analyze large amounts of data
more deeply and reveal new insights for which it might not have
been trained. For example, consider a deep learning model that is
trained to analyze consumer purchases. The model has data only
for the items you have already purchased. However, the artificial
neural network can suggest new items that you haven't bought
by comparing your buying patterns to those of other similar
customers.
• Unsupervised learning
• Deep learning models can learn and improve over time based on user
behavior. They do not require large variations of labeled datasets. For
example, consider a neural network that automatically corrects or
suggests words by analyzing your typing behavior. Let's assume it
was trained in the English language and can spell-check English
words. However, if you frequently type non-English words, such
as danke, the neural network automatically learns and autocorrects
these words too.
• Volatile data processing
• Volatile datasets have large variations. One example is loan
repayment amounts in a bank. A deep learning neural network can
categorize and sort that data as well, such as by analyzing financial
transactions and flagging some of them for fraud detection.
• What are the challenges of deep learning?
• As deep learning is a relatively new technology, certain challenges come with its
practical implementation.
• Large quantities of high-quality data
• Deep learning algorithms give better results when you train them on large
amounts of high-quality data. Outliers or mistakes in your input dataset can
significantly affect the deep learning process. For instance, in our animal image
example, the deep learning model might classify an airplane as a turtle if non-
animal images were accidentally introduced in the dataset.
• To avoid such inaccuracies, you must clean and process large amounts of data
before you can train deep learning models. The input data preprocessing requires
large amounts of data storage capacity.
• Large processing power
• Deep learning algorithms are compute-intensive and require infrastructure with
sufficient compute capacity to properly function. Otherwise, they take a long
time to process results.
• Types of deep learning models
• Deep learning algorithms are incredibly complex, and there
are different types of neural networks to address specific
problems or datasets. Here are six. Each has its own
advantages and they are presented here roughly in the order
of their development, with each successive model adjusting
to overcome a weakness in a previous model.
• One potential weakness across them all is that deep learning
models are often “black boxes,” making it difficult to
understand their inner workings and posing interpretability
challenges. But this can be balanced against the overall
benefits of high accuracy and scalability.
• CNNs
• Convolutional neural networks (CNNs or ConvNets) are used
primarily in computer vision and image classification applications.
They can detect features and patterns within images and videos,
enabling tasks such as object detection, image recognition, pattern
recognition and face recognition. These networks harness principles
from linear algebra, particularly matrix multiplication, to identify
patterns within an image.
• CNNs are a specific type of neural network, which is composed of
node layers, containing an input layer, one or more hidden layers
and an output layer. Each node connects to another and has an
associated weight and threshold. If the output of any individual
node is above the specified threshold value, that node is activated,
sending data to the next layer of the network. Otherwise, no data is
passed along to the next layer of the network.
• At least three main types of layers make up a CNN: a
convolutional layer, pooling layer and fully connected (FC)
layer. For complex uses, a CNN might contain up to
thousands of layers, each layer building on the previous
layers. By “convolution”—working and reworking the original
input—detailed patterns can be discovered. With each layer,
the CNN increases in its complexity, identifying greater
portions of the image. Earlier layers focus on simple features,
such as colors and edges. As the image data progresses
through the layers of the CNN, it starts to recognize larger
elements or shapes of the object until it finally identifies the
intended object.
• CNNs are distinguished from other neural networks by their
superior performance with image, speech or audio signal
inputs. Before CNNs, manual and time-consuming feature
extraction methods were used to identify objects in images.
However, CNNs now provide a more scalable approach to
image classification and object recognition tasks, and process
high-dimensional data. And CNNs can exchange data
between layers, to deliver more efficient data processing.
While information might be lost in the pooling layer, this
might be outweighed by the benefits of CNNs, which can help
to reduce complexity, improve efficiency and limit risk of
overfitting.
• CNNs are distinguished from other neural networks by their
superior performance with image, speech or audio signal
inputs. Before CNNs, manual and time-consuming feature
extraction methods were used to identify objects in images.
However, CNNs now provide a more scalable approach to
image classification and object recognition tasks, and process
high-dimensional data. And CNNs can exchange data
between layers, to deliver more efficient data processing.
While information might be lost in the pooling layer, this
might be outweighed by the benefits of CNNs, which can help
to reduce complexity, improve efficiency and limit risk of
overfitting.
• RNNs
• Recurrent neural networks (RNNs) are typically used in
natural language and speech recognition applications as they
use sequential or time-series data. RNNs can be identified by
their feedback loops. These learning algorithms are primarily
used when using time-series data to make predictions about
future outcomes. Use cases include stock market predictions
or sales forecasting, or ordinal or temporal problems, such as
language translation, natural language processing (NLP),
speech recognition and image captioning. These functions
are often incorporated into popular applications such as Siri,
voice search and Google Translate.
• RNNs use their “memory” as they take information from prior
inputs to influence the current input and output. While
traditional deep neural networks assume that inputs and
outputs are independent of each other, the output of RNNs
depends on the prior elements within the sequence. While
future events would also be helpful in determining the output
of a given sequence, unidirectional recurrent neural networks
cannot account for these events in their predictions.
• RNNs share parameters across each layer of the network and share
the same weight parameter within each layer of the network, with
the weights adjusted through the processes of backpropagation and
gradient descent to facilitate reinforcement learning.
• RNNs use a backpropagation through time (BPTT) algorithm to
determine the gradients, which is slightly different from traditional
backpropagation as it is specific to sequence data. The principles of
BPTT are the same as traditional backpropagation, where the model
trains itself by calculating errors from its output layer to its input
layer. BPTT differs from the traditional approach in that BPTT sums
errors at each time step, whereas feedforward networks do not need
to sum errors as they do not share parameters across each layer.
• An advantage over other neural network types is that RNNs
use both binary data processing and memory. RNNs can plan
out multiple inputs and productions so that rather than
delivering only one result for a single input, RMMs can
produce one-to-many, many-to-one or many-to-many
outputs.
• Autoencoders and variational autoencoders
• Deep learning made it possible to move beyond the analysis of
numerical data, by adding the analysis of images, speech and other
complex data types. Among the first class of models to achieve this
were variational autoencoders (VAEs). They were the first deep-learning
models to be widely used for generating realistic images and speech,
which empowered deep generative modeling by making models easier
to scale—which is the cornerstone of what we think of as generative AI.
• Autoencoders work by encoding unlabeled data into a compressed
representation, and then decoding the data back into its original
form. Plain autoencoders were used for a variety of purposes, including
reconstructing corrupted or blurry images. Variational autoencoders
added the critical ability not just to reconstruct data, but also to output
variations on the original data.
• Autoencoders are built out of blocks of encoders and decoders, an
architecture that also underpins today’s large language models. Encoders
compress a dataset into a dense representation, arranging similar data
points closer together in an abstract space. Decoders sample from this
space to create something new while preserving the dataset’s most
important features.
• The biggest advantage to autoencoders is the ability to handle large batches
of data and show input data in a compressed form, so the most significant
aspects stand out—enabling anomaly detection and classification tasks. This
also speeds transmission and reduces storage requirements. Autoencoders
can be trained on unlabeled data so they might be used where labeled data
is not available. When unsupervised training is used, there is a time savings
advantage: deep learning algorithms learn automatically and gain accuracy
without needing manual feature engineering. In addition, VAEs can generate
new sample data for text or image generation.
• GANs
• Generative adversarial networks (GANs) are neural networks
that are used both in and outside of artificial intelligence (AI)
to create new data resembling the original training data.
These can include images appearing to be human faces—but
are generated, not taken of real people. The “adversarial”
part of the name comes from the back-and-forth between the
two portions of the GAN: a generator and a discriminator.
• The generator creates something: images, video or audio
and then producing an output with a twist. For example, a
horse can be transformed into a zebra with some degree of
accuracy. The result depends on the input and how well-
trained the layers are in the generative model for this use
case.
• The discriminator is the adversary, where
the generative result (fake image) is compared against
the real images in the dataset. The discriminator tries to
distinguish between the real and fake images, video or audio.
• GANs train themselves. The generator creates fakes while the
discriminator learns to spot the differences between the generator's
fakes and the true examples. When the discriminator is able to flag the
fake, then the generator is penalized. The feedbaccreating realistic
output that can be difficult to distinguish from the originals, which in
turn may be used to further train machine learning models. Setting up
a GAN to learn is straightforward, since they are trained by using
unlabeled data or with minor labeling. However, the potential
disadvantage is that the generator and discriminator might go back-
and-forth in competition for a long time, creating a large system drain.
One training limitation is that a huge amount of input data might be
required to obtain a satisfactory output. Another potential problem is
“mode collapse,” when the generator produces a limited set of ok loop
continues until the generator succeeds in producing output that the
discriminator cannot distinguish.
• The prime GAN benefit is utputs rather than a wider variety.
REINFORCEMENT LEARNING

• Reinforcement learning (RL) is a machine learning (ML)

technique that trains software to make decisions to achieve
the most optimal results. It mimics the trial-and-error learning
process that humans use to achieve their goals.
• Main examples of Reinforcement Learning -
• Predictive text, text summarization, question answering, and
machine translation are all examples of natural language
processing (NLP) that uses reinforcement learning. By
studying typical language patterns, RL agents can mimic and
predict how people speak to each other every day
• Reinforcement learning is based on rewarding desired
behaviors and punishing undesired ones. In general, a
reinforcement learning agent -- the software entity being
trained -- is able to perceive and interpret its environment, as
well as take actions and learn through trial and error.
• Relating reinforced learning with real life-
• Reinforcement learning (RL) is a learning mode in which a
computer interacts with an environment, receives feedback
and, based on that, adjusts its decision-making strategy.
Deep reinforcement learning is a specialized form of RL that
utilizes deep neural networks to solve more complex
problems.
• There are several algorithms that can be used to train
reinforcement learning agents, such as Q-learning, policy
gradient methods, and actor-critic methods. These algorithms
differ in how they estimate the expected cumulative reward
and update the agent's policy.
• Breaking it down, the process of Reinforcement
Learning involves these simple steps:
1.Observation of the environment.
2.Deciding how to act using some strategy.
3.Acting accordingly.
4.Receiving a reward or penalty.
5.Learning from the experiences and refining our strategy.
6.Iterate until an optimal strategy is found.
• Reinforcement Learning: An Overview
• Reinforcement Learning (RL) is a branch of machine learning
focused on making decisions to maximize cumulative
rewards in a given situation. Unlike supervised learning,
which relies on a training dataset with predefined answers,
RL involves learning through experience. In RL, an agent
learns to achieve a goal in an uncertain, potentially complex
environment by performing actions and receiving feedback
through rewards or penalties.
• Key Concepts of Reinforcement Learning
• Agent: The learner or decision-maker.
• Environment: Everything the agent interacts with.
• State: A specific situation in which the agent finds itself.
• Action: All possible moves the agent can make.
• Reward: Feedback from the environment based on the
action taken.
• How Reinforcement Learning Works
• RL operates on the principle of learning optimal behavior through trial and
error. The agent takes actions within the environment, receives rewards or
penalties, and adjusts its behavior to maximize the cumulative reward. This
learning process is characterized by the following elements:
• Policy: A strategy used by the agent to determine the next action based on
the current state.
• Reward Function: A function that provides a scalar feedback signal based
on the state and action.
• Value Function: A function that estimates the expected cumulative reward
from a given state.
• Model of the Environment: A representation of the environment that helps
in planning by predicting future states and rewards.
• Example: Navigating a Maze
• The problem is as follows: We have an agent and a reward,
with many hurdles in between. The agent is supposed to find
the best possible path to reach the reward. The following
problem explains the problem more easily.
• The above image shows the robot, diamond, and fire. The
goal of the robot is to get the reward that is the diamond and
avoid the hurdles that are fired. The robot learns by trying all
the possible paths and then choosing the path which gives
him the reward with the least hurdles. Each right step will
give the robot a reward and each wrong step will subtract the
reward of the robot. The total reward will be calculated when
it reaches the final reward that is the diamond.
• Main points in Reinforcement learning –
• Input: The input should be an initial state from which the
model will start
• Output: There are many possible outputs as there are a
variety of solutions to a particular problem
• Training: The training is based upon the input, The model will
return a state and the user will decide to reward or punish
the model based on its output.
• The model keeps continues to learn.
• The best solution is decided based on the maximum reward.
• Difference between Reinforcement learning and
Supervised learning:
Reinforcement learning Supervised learning

Reinforcement learning is all In Supervised learning, the

about making decisions decision is made on the initial
sequentially. In simple words, we input or the input given at the
can say that the output depends start
on the state of the current input
and the next input depends on
the output of the previous input
In Reinforcement learning In supervised learning the
decision is dependent, So we decisions are independent of
give labels to sequences of each other so labels are given to
dependent decisions each decision.
Example: Chess game,text Example: Object
summarization recognition,spam detetction
• Types of Reinforcement:
1.Positive: Positive Reinforcement is defined as when an
event, occurs due to a particular behavior, increases the
strength and the frequency of the behavior. In other words, it
has a positive effect on behavior.
Advantages of reinforcement learning are:

1.Maximizes Performance
2.Sustain Change for a long period of time
3.Too much Reinforcement can lead to an overload of states which can
diminish the results
2.Negative: Negative Reinforcement is defined as
strengthening of behavior because a negative condition is
stopped or avoided.
Advantages of reinforcement learning:

2.Increases Behavior
3.Provide defiance to a minimum standard of performance
4.It Only provides enough to meet up the minimum behavior
• Elements of Reinforcement Learning
• i) Policy: Defines the agent’s behavior at a given time.
• ii) Reward Function: Defines the goal of the RL problem by
providing feedback.
• iii) Value Function: Estimates long-term rewards from a
state.
• iv) Model of the Environment: Helps in predicting future
states and rewards for planning.
• Application of Reinforcement Learnings
• i) Robotics: Automating tasks in structured environments
like manufacturing.
• ii) Game Playing: Developing strategies in complex games
like chess.
• iii) Industrial Control: Real-time adjustments in operations
like refinery controls.
• iv) Personalized Training Systems: Customizing
instruction based on individual needs.
• Advantages and Disadvantages of Reinforcement Learning
• Advantages:
• 1. Reinforcement learning can be used to solve very complex problems
that cannot be solved by conventional techniques.
• 2. The model can correct the errors that occurred during the training
process.
• 3. In RL, training data is obtained via the direct interaction of the agent
with the environment
• 4. Reinforcement learning can handle environments that are non-
deterministic, meaning that the outcomes of actions are not always
predictable. This is useful in real-world applications where the
environment may change over time or is uncertain.
• 5. Reinforcement learning can be used to solve a wide range
of problems, including those that involve decision making,
control, and optimization.
• 6. Reinforcement learning is a flexible approach that can be
combined with other machine learning techniques, such as
deep learning, to improve performance.
• Disadvantages:
• 1. Reinforcement learning is not preferable to use for solving
simple problems.
• 2. Reinforcement learning needs a lot of data and a lot of
computation
• 3. Reinforcement learning is highly dependent on the quality of
the reward function. If the reward function is poorly designed,
the agent may not learn the desired behavior.
• 4. Reinforcement learning can be difficult to debug and interpret.
It is not always clear why the agent is behaving in a certain way,
which can make it difficult to diagnose and fix problems.
• Conclusion
• Reinforcement learning is a powerful technique for decision-
making and optimization in dynamic environments. Its
applications range from robotics to personalized learning
systems. However, the complexity of RL requires careful
design of reward functions and significant computational
resources. By understanding its principles and applications,
one can leverage RL to solve intricate real-world problems.
TRANSFER LEARNING

• Transfer learning is a machine learning technique in which knowledge

gained through one task or dataset is used to improve model
performance on another related task and/or different dataset. In other
words, transfer learning uses what has been learned in one setting to
improve generalization in another setting
• Transfer learning in Natural Language Processing (NLP) uses pre-trained
language models to improve performance across tasks like text
classification and machine translation, adapting them to specific
domains through fine-tuning for efficient development and deployment.
• Stages of transfer learning
• (a) First stage transfer: fine-tuning with an adaptive fully
connected layer.
• (b) Second stage transfer: knowledge transfer with soft labels
for joint learning.
• In the first stage, the network is fine-tuned by the labeled
image while predicting the soft labels for the unlabeled
image.
• Difference between transfer learning and deep learning
• Transfer learning is a specific technique in machine learning
that involves reusing a model and its knowledge for learning
another task. Meanwhile, deep learning is a type of machine
learning that involves using artificial neural networks to
mimic the way humans learn.
• We, humans, are very good at applying the transfer of
knowledge between tasks. This means that whenever we
encounter a new problem or a task. Similarly Transfer
learning is a smart method in machine learning where a
model uses knowledge from one task to help with a
different, but related, task. Instead of learning from zero,
the model uses what it already knows to solve new problems
faster and better.
• This is especially helpful when there isn’t much data
available. Transfer learning is making a big impact in
areas like understanding language and recognizing
images.
• What is Transfer Learning?
• Transfer learning is a technique in machine learning where a
model trained on one task is used as the starting point for a
model on a second task. This can be useful when the second
task is similar to the first task, or when there is limited data
available for the second task. By using the learned features
from the first task as a starting point, the model can learn
more quickly and effectively on the second task. This can
also help to prevent overfitting, as the model will have
already learned general features that are likely to be useful in
the second task.
• Why do we need Transfer Learning?
• Transfer learning is essential in machine learning for several
reasons:
• Limited Data: In many real-world scenarios, obtaining a large
amount of labeled data for training a model from scratch can be
difficult and expensive. Transfer learning allows us to leverage pre-
trained models and their knowledge, reducing the need for vast
amounts of data.
• Improved Performance: By starting with a pre-trained model,
which has already learned from a large dataset, we can achieve
better performance on new tasks more quickly. This is especially
useful in applications where accuracy and efficiency are crucial.
• Time and Cost Efficiency: Transfer learning saves time and
resources because it speeds up the training process. Instead
of training a new model from scratch, we can build on
existing models and fine-tune them for specific tasks.
• Adaptability: Models trained on one task can be adapted to
perform well on related tasks. This adaptability makes
transfer learning suitable for a wide range of applications,
from image recognition to natural language processing.
• How does Transfer Learning work?
• This is a general summary of how transfer learning works:
• Pre-trained Model: Start with a model that has previously been trained
for a certain task using a large set of data. Frequently trained on extensive
datasets, this model has identified general features and patterns relevant
to numerous related jobs.
• Base Model: The model that has been pre-trained is known as the base
model. It is made up of layers that have utilized the incoming data to learn
hierarchical feature representations.
• Transfer Layers: In the pre-trained model, find a set of layers that capture
generic information relevant to the new task as well as the previous one.
Because they are prone to learning low-level information, these layers are
frequently found near the top of the network.
• Fine-tuning: Using the dataset from the new challenge to
retrain the chosen layers. We define this procedure as fine-
tuning. The goal is to preserve the knowledge from the pre-
training while enabling the model to modify its parameters to
better suit the demands of the current assignment.
• Low-level features learned for task A should be beneficial
for learning of model for task B.
• In transfer learning, “frozen” layers refer to pre-trained layers
whose weights remain fixed during subsequent training,
preserving learned features. These layers are not updated to
prevent loss of valuable knowledge. In contrast, “trainable”
layers are those modified and fine-tuned on the new task,
allowing the model to adapt to task-specific patterns.
FEEZED AND TRAINABLE LAYERS

• Feezed and trainable layers

• In transfer learning, there are two main components: frozen layers and
modifiable layers.
1.Frozen Layers: These are the layers of a pre-trained model that are kept
unchanged during the fine-tuning process. Frozen layers retain the
knowledge learned from the original task and are used to extract general
features from the input data.
2.Modifiable Layers: These are the layers of the model that are adjusted or
re-trained during fine-tuning. Modifiable layers learn task-specific features
from the new dataset. By focusing on these layers, the model can adapt to
the specific requirements of the new task.
3.Now, one may ask how to determine which layers we need to freeze, and
which layers need to train. The answer is simple, the more you want to
inherit features from a pre-trained model, the more you have to freeze
layers.
• Let’s consider all situations where the size and dataset of the
target task vary from the base network.
• The target dataset is small and similar to the base
network dataset: Since the target dataset is small, that
means we can fine-tune the pre-trained network with the
target dataset. But this may lead to a problem of overfitting.
Also, there may be some changes in the number of classes in
the target task. So, in such a case we remove the fully
connected layers from the end, maybe one or two, and add a
new fully connected layer satisfying the number of new
classes. Now, we freeze the rest of the model and only train
newly added layers.
• The target dataset is large and similar to the base training dataset: In
such cases when the dataset is large, and it can hold a pre-trained model there
will be no chance of overfitting. Here, also the last full-connected layer is
removed, and a new fully-connected layer is added with the proper number of
classes. Now, the entire model is trained on a new dataset. This makes sure to
tune the model on a new large dataset keeping the model architecture the
same.
• The target dataset is small and different from the base network
dataset: Since the target dataset is different, using high-level features of the
pre-trained model will not be useful. In such a case, remove most of the layers
from the end in a pre-trained model, and add new layers a satisfying number of
classes in a new dataset. This way we can use low-level features from the pre-
trained model and train the rest of the layers to fit a new dataset. Sometimes, it
is beneficial to train the entire network after adding a new layer at the end.
• The target dataset is large and different from the base
network dataset: Since the target network is large and
different, the best way is to remove the last layers from the
pre-trained network and add layers with a satisfying number
of classes, then train the entire network without freezing any
layer.
• Advantages of transfer learning:
• Speed up the training process: By using a pre-trained model, the
model can learn more quickly and effectively on the second task,
as it already has a good understanding of the features and
patterns in the data.
• Better performance: Transfer learning can lead to better
performance on the second task, as the model can leverage the
knowledge it has gained from the first task.
• Handling small datasets: When there is limited data available for
the second task, transfer learning can help to prevent overfitting,
as the model will have already learned general features that are
likely to be useful in the second task.
• Disadvantages of transfer learning:
• Domain mismatch: The pre-trained model may not be well-suited to the second
task if the two tasks are vastly different or the data distribution between the two
tasks is very different.
• Overfitting: Transfer learning can lead to overfitting if the model is fine-tuned too
much on the second task, as it may learn task-specific features that do not
generalize well to new data.
• Complexity: The pre-trained model and the fine-tuning process can be
computationally expensive and may require specialized hardware.
• Conclusion
• Transfer learning is a powerful technique in machine learning that enhances model
performance by leveraging knowledge from previously trained models. By starting
with pre-existing models and fine-tuning them for specific tasks, transfer learning
saves time, improves accuracy, and enables effective learning even with limited
data.
• Incremental learning is a methodology of machine learning where
INCREMENTAL LEARNING
an AI model learns and enhances its knowledge progressively,
without forgetting previously acquired information. In essence, it
imitates human learning patterns by acquiring new information
over time, while maintaining and building upon previous
knowledge.
• Incremental approach means processing knowledge in small bits
and in small steps. gradually converting the learning materials
into lasting knowledge in your memory. This conversion may also
produce an easily searchable and well-annotated computer media
archive that does not even need to be part of the learning
process.
• In computer science, incremental learning is a method of
machine learning in which input data is continuously used to extend
the existing model's knowledge i.e. to further train the model. It
represents a dynamic technique of supervised learning and
unsupervised learning that can be applied when training data
becomes available gradually over time or its size is out of system
memory limits. Algorithms that can facilitate incremental learning are
known as incremental machine learning algorithms.
• The aim of incremental learning is for the learning model to adapt to
new data without forgetting its existing knowledge. Some incremental
learners have built-in some parameter or assumption that controls the
relevancy of old data, while others, called stable incremental machine
learning algorithms, learn representations of the training data that are
not even partially forgotten over time. Fuzzy ART[10] and TopoART[7]
are two examples for this second approach.
• Many traditional machine learning algorithms inherently support
incremental learning. Other algorithms can be adapted to facilitate
incremental learning
• The aim of incremental learning is for the learning model to adapt to
new data without forgetting its existing knowledge. Some incremental
learners have built-in some parameter or assumption that controls the
relevancy of old data, while others, called stable incremental machine
learning algorithms, learn representations of the training data that are
not even partially forgotten over time. Fuzzy ART and TopoARTare two
examples for this second approach.
• Incremental algorithms are frequently applied to data streams or
big data, addressing issues in data availability and resource scarcity
respectively. Stock trend prediction and user profiling are some
examples of data streams where new data becomes continuously
available. Applying incremental learning to big data aims to produce
faster classification or forecasting times.
• What is Natural Language Processing (NLP) Chatbots?
• Natural Language Processing (NLP) chatbots are computer
programs designed to interact with users in natural language,
enabling seamless communication between humans and
machines. These chatbots use various NLP techniques to
understand, interpret, and generate human language,
allowing them to comprehend user queries, extract relevant
information, and provide appropriate responses. In this
article, we will discuss chatbots thoroughly.
• What are chatbots?
• Chatbots are software applications designed to engage in conversations
with users, either through text or voice interfaces, by utilizing
artificial intelligence and natural language processing techniques. Rule-
based chatbots operate on predefined rules and patterns, while AI-
powered chatbots leverage machine learning algorithms to understand
and respond to natural language input. These chatbots find widespread
use across various industries, including customer service, sales,
healthcare, and finance, offering businesses an efficient means to
automate processes, provide instant support, and enhance user
engagement. By simulating human-like interactions, chatbots enable
seamless communication between users and technology, transforming
the way businesses interact with their customers and users.
• Types of NLP Chatbots
• NLP chatbots come in various types, each designed to serve different purposes
and leverage different NLP techniques. A few of them are as follows:
•A fewRetrieval-Based Chatbots: These chatbots choose the most
appropriate answers based on their learning. Access-based chatbots use
predefined responses, strategizing, target recognition, response options,
content management, feedback, and more. They also use technologies such as
natural language understanding (NLU) to produce human-like responses.
• Generative Chatbots: Generative AI chatbots create new answers from
scratch based on learning data. These bots use large language models (LLMs).
The most popular LLM in 2023 is ChatGPT, but there are many different LLMs
and different methods and these systems will evolve rapidly in the coming
months. Chatbots use LLM to understand user input, generate responses,
enable conversation to flow across multiple interactions, generate content,
transform/learn, and more.
• Hybrid Chatbots: Hybrid chatbots are conversational AI that
combines various technologies and methods to provide a versatile
and effective experience. These chatbots often combine custom
rules with machine learning and artificial intelligence tools. female
gender. It combines proprietary and machine learning-based
content to provide an overall comprehensive discussion.
• Contextual Chatbots: Content chatbots are virtual assistants
designed to engage in human-like conversations with users,
providing personalized and helpful service. Contextual Chatbots
Chatbots use NLP and ML to understand the context of the
conversation and respond accordingly. They can solve complex
questions, learn from user interaction, and provide more human
and personal information.
• Working of NLP Chatbots
• The workings of NLP chatbots involve several key components that enable them
to understand, interpret, and generate human language in a conversational
manner. Here’s a simplified overview of how NLP chatbots function:
1.Input Processing: When a user sends a message or query to the chatbot, the
input is first processed to extract relevant information. This involves tasks such
as tokenization (breaking the text into words or tokens), part-of-speech tagging
(identifying the grammatical components of each word), and named entity
recognition (identifying important entities such as names, dates, and locations).
2.Intent Recognition: After processing the input, the chatbot identifies the
user’s intent or the purpose behind the message. This involves understanding
what the user wants to accomplish, such as asking a question, making a
request, or providing feedback.
3.Dialogue Management: Once the intent is recognized, the chatbot manages the
conversation flow by keeping track of the context and history of the interaction. It
determines the appropriate response based on the current dialogue state and the user’s
intent.
4.Response Generation: After understanding the user’s intent and context, the chatbot
generates a response. This can involve retrieving information from a knowledge base,
executing commands, or generating a natural language response using techniques such as
text generation and natural language generation.
5.Feedback and Learning: NLP chatbots often incorporate machine learning algorithms to
improve their performance over time. They learn from user interactions and feedback to
enhance their understanding of language and the accuracy of their responses.
6.Output Rendering: Finally, the chatbot delivers the response back to the user in a
human-readable format, such as text or speech
7.Overall, the workings of NLP chatbots involve a combination of text processing, intent
recognition, dialogue management, response generation, and machine learning techniques
to enable natural and intuitive interactions between humans and machines.
DIFFERENCE BETWEEN TRADITIONAL
CHATBOTS VS NLP CHATBOTS

Features Traditional Chatbot NLP Chatbot

How do they work? Keyword-based AI-based

How scalable are they? Limited scalability Unlimited scalability

How are they updated? Must be trained explicitly Learns from each interaction

How do customers Button-focused interaction Text and voice

interact with them?
How much can them Only what it has been pre-trained to
Almost anything, thanks to Automatic
understand? Semantic Understanding
• Uses of NLP Chatbots
• NLP chatbots find diverse applications across various industries and domains
due to their ability to understand and generate human-like language. Some
common uses of NLP chatbots include:
1.Customer Service: NLP chatbots are widely used in customer service to
provide instant assistance and support to customers. They can answer
frequently asked questions, troubleshoot issues, and handle basic inquiries,
thereby reducing the workload on human support agents and improving
customer satisfaction.
2.Virtual Assistants: NLP chatbots serve as virtual assistants, helping users
with tasks such as setting reminders, scheduling appointments, sending
notifications, and providing personalized recommendations. Popular virtual
assistants like Siri, Alexa, and Google Assistant leverage NLP to understand
user commands and perform tasks accordingly.
3.E-commerce: NLP chatbots enhance the shopping experience by assisting users with
product search, recommendations, and purchase decisions. They can answer product-
related queries, provide information about order status and shipping details, and offer
personalized shopping suggestions based on user preferences and browsing history.
4.Healthcare: In the healthcare industry, NLP chatbots are used for patient engagement,
remote monitoring, and health-related consultations. They can provide medical advice,
answer health-related questions, remind patients to take medication, and schedule
appointments with healthcare providers.
5.Education: NLP chatbots are utilized in educational settings to facilitate learning and
provide personalized tutoring. They can answer students’ questions, provide
explanations of complex concepts, offer study tips, and deliver interactive learning
experiences through quizzes and simulations.
6.Finance: NLP chatbots assist users with financial tasks such as checking account
balances, transferring funds, paying bills, and managing budgets. They can provide
personalized financial advice, help users track expenses, and offer insights into
investment opportunities based on market trends and user preferences.
7.HR and Recruitment: NLP chatbots streamline the recruitment process by
automating tasks such as resume screening, candidate pre-screening
interviews, and scheduling interviews. They can engage with job applicants,
answer questions about job openings and company policies, and provide
status updates on application submissions.
8.Travel and Hospitality: NLP chatbots enhance the travel experience by
assisting users with travel planning, booking flights and accommodations,
and providing destination recommendations. They can answer travel-related
queries, offer local information and travel tips, and handle customer support
inquiries during the trip.
• Overall, NLP chatbots play a crucial role in improving efficiency, enhancing
user experience, and driving innovation across various industries, offering
organizations valuable tools for automation, customer engagement, and
service delivery.
• Challenges of NLP Chatbots
• Despite their numerous benefits, NLP chatbots face several challenges that can
affect their performance and usability. Some of the key challenges include:
1.Understanding Natural Language: Natural language is inherently complex
and nuanced, making it challenging for chatbots to accurately understand user
queries and intents. Ambiguity, slang, spelling errors, and colloquialisms further
complicate the task of natural language understanding.
2.Contextual Understanding: NLP chatbots often struggle to maintain context
and understand the nuances of ongoing conversations. They may misinterpret
user messages or fail to recognize changes in context, leading to irrelevant or
inaccurate responses.
3.Handling Complex Queries: Chatbots may struggle to handle complex or multi-
turn queries that require deep understanding and reasoning. Tasks such as
answering open-ended questions, providing explanations, and solving complex
problems pose significant challenges for NLP chatbots.
4.Data Limitations: NLP chatbots rely heavily on training data to learn language
patterns and generate responses. Limited or biased training data can result in poor
performance, as chatbots may fail to capture the diversity of language usage and
user preferences.
5.Personalization and User Engagement: Delivering personalized experiences and
engaging users in meaningful conversations is challenging for NLP chatbots. They
may struggle to adapt to individual preferences, maintain user interest over time, and
provide relevant recommendations or responses.
6.Privacy and Security Concerns: NLP chatbots may handle sensitive information
such as personal data, financial details, and health records. Ensuring the privacy and
security of user data is essential to build trust and comply with regulatory
requirements.
7.Ethical Considerations: Chatbots can inadvertently perpetuate biases and
stereotypes present in training data, leading to unfair or discriminatory outcomes.
Ethical concerns such as transparency, fairness, and accountability must be
addressed to mitigate potential harm to users.
8.Integration with Other Systems: Integrating NLP chatbots with existing
systems and platforms can be challenging, particularly in complex
enterprise environments. Ensuring seamless interoperability and data
exchange requires careful planning and coordination.
9.Continuous Learning and Improvement: NLP chatbots need to
continuously learn from user interactions and feedback to improve their
performance over time. Implementing effective mechanisms for learning,
adaptation, and feedback loop is essential for enhancing chatbot
capabilities.
• Addressing these challenges requires advancements in NLP techniques,
robust training data, thoughtful design, and ongoing evaluation and
optimization of chatbot performance. Despite the hurdles, overcoming
these challenges can unlock the full potential of NLP chatbots to
revolutionize human-computer interaction and drive innovation across
various domains.
• What is the future of NLP Chatbots?
• The future of NLP chatbots holds immense promise, driven by advancements in
artificial intelligence, natural language processing, and human-computer interaction.
Here are some key trends and possibilities shaping the future of NLP chatbots:

1.Advancements in AI and NLP: Continued progress in AI and NLP technologies will

lead to chatbots with enhanced capabilities for understanding, reasoning, and
generating human-like responses. Deep learning techniques, such as transformer
models like GPT (Generative Pre-trained Transformer), will enable chatbots to
comprehend context more accurately and generate more contextually relevant
responses.
2.Conversational AI Assistants: NLP chatbots will evolve into sophisticated
conversational AI assistants that can handle complex tasks and engage in meaningful,
context-aware conversations with users. These assistants will integrate seamlessly into
various applications and platforms, offering personalized assistance and automating a
wide range of tasks across different domains.
3.Multimodal Interaction: Future NLP chatbots will support multimodal
interaction, allowing users to engage through a combination of text, voice,
images, and gestures. Integrating speech recognition, computer vision, and
other modalities will enable more natural and intuitive interactions, enhancing
user experience and accessibility.
4.Hyper-personalization: NLP chatbots will leverage user data and contextual
information to deliver hyper-personalized experiences tailored to individual
preferences, behavior, and history. They will anticipate user needs, provide
proactive recommendations, and adapt their responses dynamically based on
user context and feedback.
5.Integration with IoT and Smart Devices: NLP chatbots will be integrated
with IoT devices and smart environments, enabling users to interact with their
surroundings using natural language commands. They will act as central hubs
for controlling smart home devices, accessing information, and managing daily
tasks, offering seamless connectivity and convenience.
6.Domain-specific Applications: NLP chatbots will be increasingly specialized for
specific industries and use cases, offering tailored solutions and expertise in areas
such as healthcare, finance, education, customer service, and more. Domain-
specific chatbots will provide deeper insights, domain-specific knowledge, and
industry-specific functionalities to meet the unique needs of users.
7.Ethical AI and Responsible Design: With growing concerns about AI ethics and
bias, the future of NLP chatbots will prioritize ethical considerations, fairness,
transparency, and accountability. Chatbot developers will adopt responsible AI
practices and design principles to mitigate biases, ensure privacy and security,
and promote inclusivity and diversity.
8.Human-Centered Design and Collaboration: NLP chatbots will be designed
with a focus on human-centered principles, emphasizing empathy, empathy, and
user empowerment. They will collaborate seamlessly with human counterparts,
augmenting human capabilities, and enhancing productivity and creativity
through synergistic human-computer interaction.
• Overall, the future of NLP chatbots is bright, offering exciting opportunities to
transform how we interact with technology, access information, and accomplish
tasks in our daily lives. As NLP chatbots continue to evolve and mature, they will
play an increasingly integral role in shaping the future of human-computer
interaction and driving innovation across diverse domains.
• Conclusion:
• NLP chatbots represent a significant advancement in AI, enabling intuitive, human-
like interactions across various industries. Despite challenges in understanding
context, handling language variability, and ensuring data privacy, ongoing
technological improvements promise more sophisticated and effective chatbots.
The future holds enhanced contextual and emotional understanding, multilingual
support, and seamless integration with everyday technologies. These
developments will make NLP chatbots indispensable in improving customer
service, automating tasks, and providing personalized experiences, ultimately
bridging the gap between human communication and machine understanding.
EDGE AI
• What Is Edge AI?
• Edge AI is the deployment of AI applications in devices throughout
the physical world. It’s called “edge AI” because the AI
computation is done near the user at the edge of the network,
close to where the data is located, rather than centrally in a cloud
computing facility or private data center.
• Since the internet has global reach, the edge of the network can
connote any location. It can be a retail store, factory, hospital or
devices all around us, like traffic lights, autonomous machines and
phones.
• Edge AI: Why Now?
• Organizations from every industry are looking to increase
automation to improve processes, efficiency and safety.
• To help them, computer programs need to recognize patterns and
execute tasks repeatedly and safely. But the world is unstructured
and the range of tasks that humans perform covers infinite
circumstances that are impossible to fully describe in programs and
rules.
• Advances in edge AI have opened opportunities for machines and
devices, wherever they may be, to operate with the “intelligence” of
human cognition. AI-enabled smart applications learn to perform
similar tasks under different circumstances, much like real life.
• The efficacy of deploying AI models at the edge arises from three recent innovations.
1.Maturation of neural networks: Neural networks and related AI infrastructure have
finally developed to the point of allowing for generalized machine learning. Organizations
are learning how to successfully train AI models and deploy them in production at the edge.
2.Advances in compute infrastructure: Powerful distributed computational power is
required to run AI at the edge. Recent advances in highly parallel GPUs have been adapted
to execute neural networks.
3.Adoption of IoT devices: The widespread adoption of the Internet of Things has fueled
the explosion of big data. With the sudden ability to collect data in every aspect of a
business — from industrial sensors, smart cameras, robots and more — we now have the
data and devices necessary to deploy AI models at the edge. Moreover, 5G is providing IoT
a boost with faster, more stable and secure connectivity.
• Why Deploy AI at the Edge? What Are the Benefits of
Edge AI?
• Since AI algorithms are capable of understanding language,
sights, sounds, smells, temperature, faces and other analog
forms of unstructured information, they’re particularly useful
in places occupied by end users with real-world problems.
These AI applications would be impractical or even
impossible to deploy in a centralized cloud or enterprise data
center due to issues related to latency, bandwidth and
privacy.
• The benefits of edge AI include:
• Intelligence: AI applications are more powerful and flexible than
conventional applications that can respond only to inputs that the
programmer had anticipated. In contrast, an AI neural network is not trained
how to answer a specific question, but rather how to answer a particular
type of question, even if the question itself is new. Without AI, applications
couldn’t possibly process infinitely diverse inputs like texts, spoken words or
video.
• Real-time insights: Since edge technology analyzes data locally rather
than in a faraway cloud delayed by long-distance communications, it
responds to users’ needs in real time.
• Reduced cost: By bringing processing power closer to the edge,
applications need less internet bandwidth, greatly reducing networking
costs.
• Increased privacy: AI can analyze real-world information without ever exposing it
to a human being, greatly increasing privacy for anyone whose appearance, voice,
medical image or any other personal information needs to be analyzed. Edge AI
further enhances privacy by containing that data locally, uploading only the analysis
and insights to the cloud. Even if some of the data is uploaded for training purposes,
it can be anonymized to protect user identities. By preserving privacy, edge AI
simplifies the challenges associated with data regulatory compliance.
• High availability: Decentralization and offline capabilities make edge AI more
robust since internet access is not required for processing data. This results in higher
availability and reliability for mission-critical, production-grade AI applications.
• Persistent improvement: AI models grow increasingly accurate as they train on
more data. When an edge AI application confronts data that it cannot accurately or
confidently process, it typically uploads it so that the AI can retrain and learn from it.
So the longer a model is in production at the edge, the more accurate the model will
be.
• For machines to see, perform object detection, drive cars,
understand speech, speak, walk or otherwise emulate human skills,
they need to functionally replicate human intelligence.
• AI employs a data structure called a deep neural network to
replicate human cognition. These DNNs are trained to answer
specific types of questions by being shown many examples of that
type of question along with correct answers.
• This training process, known as “deep learning,” often runs in a data
center or the cloud due to the vast amount of data required to train
an accurate model, and the need for data scientists to collaborate
on configuring the model. After training, the model graduates to
become an “inference engine” that can answer real-world questions.
• In edge AI deployments, the inference engine runs on some
kind of computer or device in far-flung locations such as
factories, hospitals, cars, satellites and homes. When the AI
stumbles on a problem, the troublesome data is commonly
uploaded to the cloud for further training of the original AI
model, which at some point replaces the inference engine at
the edge. This feedback loop plays a significant role in
boosting model performance; once edge AI models are
deployed, they only get smarter and smarter.
• What Are Examples of Edge AI Use Cases?
• AI is the most powerful technology force of our time. We’re
now at a time where AI is revolutionizing the world’s largest
industries.
• Across manufacturing, healthcare, financial services,
transportation, energy and more, edge AI is driving new
business outcomes in every sector, including:
• Intelligent forecasting in energy: For critical industries such
as energy, in which discontinuous supply can threaten the health
and welfare of the general population, intelligent forecasting is
key. Edge AI models help to combine historical data, weather
patterns, grid health and other information to create complex
simulations that inform more efficient generation, distribution
and management of energy resources to customers.
• Predictive maintenance in manufacturing: Sensor data can
be used to detect anomalies early and predict when a machine
will fail. Sensors on equipment scan for flaws and alert
management if a machine needs a repair so the issue can be
addressed early, avoiding costly downtime.
• AI-powered instruments in healthcare: Modern medical
instruments at the edge are becoming AI-enabled with
devices that use ultra-low-latency streaming of surgical video
to allow for minimally invasive surgeries and insights on
demand.
• Smart virtual assistants in retail: Retailers are looking to
improve the digital customer experience by introducing voice
ordering to replace text-based searches with voice
commands. With voice ordering, shoppers can easily search
for items, ask for product information and place online orders
using smart speakers or other intelligent mobile devices.
• The Future of Edge AI
• Thanks to the commercial maturation of neural networks,
proliferation of IoT devices, advances in parallel computation
and 5G, there is now robust infrastructure for generalized
machine learning. This is allowing enterprises to capitalize on
the colossal opportunity to bring AI into their places of
business and act upon real-time insights, all while decreasing
costs and increasing privacy.
EXPLAINABLE AI
• Explainable AI is a set of tools and frameworks to help you
understand and interpret predictions made by your machine
learning models, natively integrated with a number of Google's
products and services. With it, you can debug and improve model
performance, and help others understand your models' behavior.
• For example, hospitals can use explainable AI for cancer detection
and treatment, where algorithms show the reasoning behind a
given model's decision-making. This makes it easier not only for
doctors to make treatment decisions, but also provide data-backed
explanations to their patients.
• Explainable AI (XAI) is artificial intelligence (AI) that's
programmed to describe its purpose, rationale and decision-
making process in a way that the average person can
understand. XAI helps human users understand the reasoning
behind AI and machine learning (ML) algorithms to increase
their trust.
• Explainable AI is used to describe an AI model, its expected
impact and potential biases. It helps characterize model
accuracy, fairness, transparency and outcomes in AI-powered
decision making. Explainable AI is crucial for an organization in
building trust and confidence when putting AI models into
production.
• It is crucial for an organization to have a full understanding of the AI decision-
making processes with model monitoring and accountability of AI and not to
trust them blindly. Explainable AI can help humans understand and explain
machine learning (ML) algorithms, deep learning and neural networks.
• ML models are often thought of as black boxes that are impossible to
interpret.² Neural networks used in deep learning are some of the hardest for
a human to understand. Bias, often based on race, gender, age or location,
has been a long-standing risk in training AI models. Further, AI model
performance can drift or degrade because production data differs from
training data. This makes it crucial for a business to continuously monitor and
manage models to promote AI explainability while measuring the business
impact of using such algorithms. Explainable AI also helps promote end user
trust, model auditability and productive use of AI. It also mitigates
compliance, legal, security and reputational risks of production AI.
• Explainable AI is one of the key requirements for
implementing responsible AI, a methodology for the large-
scale implementation of AI methods in real organizations with
fairness, model explainability and accountability.³ To help
adopt AI responsibly, organizations need to embed ethical
principles into AI applications and processes by building AI
systems based on trust and transparency.
HOW EXPLAINABLE AI WORKS
• With explainable AI – as well as interpretable machine learning –
organizations can gain access to AI technology’s underlying decision-
making and are empowered to make adjustments. Explainable AI can
improve the user experience of a product or service by helping the end user
trust that the AI is making good decisions. When do AI systems give enough
confidence in the decision that you can trust it, and how can the AI system
correct errors that arise?⁴
• As AI becomes more advanced, ML processes still need to be understood
and controlled to ensure AI model results are accurate. Let’s look at the
difference between AI and XAI, the methods and techniques used to turn AI
to XAI, and the difference between interpreting and explaining AI processes.
• Comparing AI and XAI
What exactly is the difference between “regular” AI and
explainable AI? XAI implements specific techniques and
methods to ensure that each decision made during the ML
process can be traced and explained. AI, on the other hand,
often arrives at a result using an ML algorithm, but the
architects of the AI systems do not fully understand how the
algorithm reached that result. This makes it hard to check for
accuracy and leads to loss of control, accountability and
auditability.
• Explainable AI techniques
The setup of XAI techniques consists of three main methods. Prediction
accuracy and traceability address technology requirements while decision
understanding addresses human needs. Explainable AI — especially
explainable machine learning — will be essential if future warfighters are to
understand, appropriately trust, and effectively manage an emerging
generation of artificially intelligent machine partners.⁵
• Prediction accuracy
Accuracy is a key component of how successful the use of AI is in everyday
operation. By running simulations and comparing XAI output to the results
in the training data set, the prediction accuracy can be determined. The
most popular technique used for this is Local Interpretable Model-Agnostic
Explanations (LIME), which explains the prediction of classifiers by the ML
algorithm.
• Traceability
Traceability is another key technique for accomplishing XAI. This is
achieved, for example, by limiting the way decisions can be made and
setting up a narrower scope for ML rules and features. An example of a
traceability XAI technique is DeepLIFT (Deep Learning Important
FeaTures), which compares the activation of each neuron to its
reference neuron and shows a traceable link between each activated
neuron and even shows dependencies between them.
• Decision understanding
This is the human factor. Many people have a distrust in AI, yet to work
with it efficiently, they need to learn to trust it. This is accomplished by
educating the team working with the AI so they can understand how
and why the AI makes decisions.
• Explainability versus interpretability in AI
• Interpretability is the degree to which an observer can understand the
cause of a decision. It is the success rate that humans can predict for the
result of an AI output, while explainability goes a step further and looks at
how the AI arrived at the result.
• How does explainable AI relate to responsible AI?
• Explainable AI and responsible AI have similar objectives, yet different
approaches. Here are the main differences between explainable and
responsible AI:
• Explainable AI looks at AI results after the results are computed.
• Responsible AI looks at AI during the planning stages to make the AI
algorithm responsible before the results are computed.
• Explainable and responsible AI can work together to make better AI.
• Continuous model evaluation
• With explainable AI, a business can troubleshoot and improve model
performance while helping stakeholders understand the behaviors of AI
models. Investigating model behaviors through tracking model insights
on deployment status, fairness, quality and drift is essential to scaling
AI.
• Continuous model evaluation empowers a business to compare model
predictions, quantify model risk and optimize model performance.
Displaying positive and negative values in model behaviors with data
used to generate explanation speeds model evaluations. A data and AI
platform can generate feature attributions for model predictions and
empower teams to visually investigate model behavior with interactive
charts and exportable documents.
• Benefits of explainable AI
• Operationalize AI with trust and confidence
• Build trust in production AI. Rapidly bring your AI models to production.
Ensure interpretability and explainability of AI models. Simplify the process
of model evaluation while increasing model transparency and traceability.
• Speed time to AI results
• Systematically monitor and manage models to optimize business outcomes.
Continually evaluate and improve model performance. Fine-tune model
development efforts based on continuous evaluation.
• Mitigate risk and cost of model governance
• Keep your AI models explainable and transparent. Manage regulatory,
compliance, risk and other requirements. Minimize overhead of manual
inspection and costly errors. Mitigate risk of unintended bias.
• Five considerations for explainable AI
• To drive desirable outcomes with explainable AI, consider the following.
• Fairness and debiasing: Manage and monitor fairness. Scan your deployment for
potential biases.
• Model drift mitigation: Analyze your model and make recommendations based on the
most logical outcome. Alert when models deviate from the intended outcomes.
• Model risk management: Quantify and mitigate model risk. Get alerted when a model
performs inadequately. Understand what happened when deviations persist.
• Lifecycle automation: Build, run and manage models as part of integrated data and AI
services. Unify the tools and processes on a platform to monitor models and share
outcomes. Explain the dependencies of machine learning models.
• Multicloud-ready: Deploy AI projects across hybrid clouds including public clouds,
private clouds and on premises. Promote trust and confidence with explainable AI.
• Use cases for explainable AI
• Healthcare: Accelerate diagnostics, image analysis, resource optimization
and medical diagnosis. Improve transparency and traceability in decision-
making for patient care. Streamline the pharmaceutical approval process
with explainable AI.
• Financial services: Improve customer experiences with a transparent loan
and credit approval process. Speed credit risk, wealth management and
financial crime risk assessments. Accelerate resolution of potential
complaints and issues. Increase confidence in pricing, product
recommendations and investment services.
• Criminal justice: Optimize processes for prediction and risk assessment.
Accelerate resolutions using explainable AI on DNA analysis, prison
population analysis and crime forecasting. Detect potential biases in training
data and algorithms.