Important Topics related to Neural Network

Supervised Learning
Supervised learning, as the name indicates, has the presence of a supervisor as a teacher.
Basically supervised learning is when we teach or train the machine using data that is well-
labeled. Which means some data is already tagged with the correct answer. After that, the
machine is provided with a new set of examples(data) so that the supervised learning algorithm
analyzes the training data(set of training examples) and produces a correct outcome from labeled
data.
For instance, suppose you are given a basket filled with different kinds of fruits. Now the first
step is to train the machine with all the different fruits one by one like this:

● If the shape of the object is rounded and has a depression at the top, is red in color,
then it will be labeled as –Apple.
● If the shape of the object is a long curving cylinder having Green-Yellow color, then
it will be labeled as –Banana.
Now suppose after training the data, you have given a new separate fruit, say Banana from the
basket, and asked to identify it.

Since the machine has already learned the things from previous data and this time has to use it
wisely. It will first classify the fruit with its shape and color and would confirm the fruit name as
BANANA and put it in the Banana category. Thus the machine learns the things from training
data(basket containing fruits) and then applies the knowledge to test data(new fruit).
Supervised learning is classified into two categories of algorithms:
● Classification: A classification problem is when the output variable is a category,
such as “Red” or “blue” , “disease” or “no disease”.
● Regression: A regression problem is when the output variable is a real value, such as
“dollars” or “weight”.
Supervised learning deals with or learns with “labeled” data. This implies that some data is
already tagged with the correct answer.
Types:-
● Regression
● Logistic Regression
● Classification
● Naive Bayes Classifiers
● K-NN (k nearest neighbors)
● Decision Trees
● Support Vector Machine
Advantages:-
● Supervised learning allows collecting data and produces data output from previous
experiences.
● Helps to optimize performance criteria with the help of experience.
● Supervised machine learning helps to solve various types of real-world computation
problems.
● It performs classification and regression tasks.
● It allows estimating or mapping the result to a new sample.
● We have complete control over choosing the number of classes we want in the
training data.
Disadvantages:-
● Classifying big data can be challenging.
● Training for supervised learning needs a lot of computation time. So, it requires a lot
of time.
● Supervised learning cannot handle all complex tasks in Machine Learning.
● Computation time is vast for supervised learning.
● It requires a labeled data set.

● It requires a training process.

Steps
Unsupervised learning
Unsupervised learning is the training of a machine using information that is neither classified
nor labeled and allowing the algorithm to act on that information without guidance. Here the task
of the machine is to group unsorted information according to similarities, patterns, and
differences without any prior training of data.
Unlike supervised learning, no teacher is provided, which means no training will be given to the
machine. Therefore the machine is restricted to find the hidden structure in unlabeled data by
itself.
For instance, suppose it is given an image having both dogs and cats which it has never seen.
Thus the machine has no idea about the features of dogs and cats so we can’t categorize it as
‘dogs and cats ‘. But it can categorize them according to their similarities, patterns, and
differences, i.e., we can easily categorize the above picture into two parts. The first may contain
all pics having dogs in them and the second part may contain all pics having cats in them. Here
you didn’t learn anything before, which means no training data or examples.
It allows the model to work on its own to discover patterns and information that was previously
undetected. It mainly deals with unlabelled data.
Unsupervised learning is classified into two categories of algorithms:
● Clustering: A clustering problem is where you want to discover the inherent
groupings in the data, such as grouping customers by purchasing behavior.
● Association: An association rule learning problem is where you want to discover
rules that describe large portions of your data, such as people that buy X also tend to
buy Y.
Types of Unsupervised Learning:-
Clustering
1. Exclusive (partitioning)
2. Agglomerative
3. Overlapping
4. Probabilistic

Clustering Types:-
1. Hierarchical clustering
2. K-means clustering
3. Principal Component Analysis
4. Singular Value Decomposition
5. Independent Component Analysis

Advantages of unsupervised learning:

● It does not require training data to be labeled.
● Dimensionality reduction can be easily accomplished using unsupervised learning.
● Capable of finding previously unknown patterns in data.
● Flexibility: Unsupervised learning is flexible in that it can be applied to a wide
variety of problems, including clustering, anomaly detection, and association rule
mining.
● Exploration: Unsupervised learning allows for the exploration of data and the
discovery of novel and potentially useful patterns that may not be apparent from the
outset.
 ● Low cost: Unsupervised learning is often less expensive than supervised learning
because it doesn’t require labeled data, which can be time-consuming and costly to
obtain.
Disadvantages of unsupervised learning :
● Difficult to measure accuracy or effectiveness due to lack of predefined answers
during training.
● The results often have lesser accuracy.
● The user needs to spend time interpreting and label the classes which follow that
classification.
● Lack of guidance: Unsupervised learning lacks the guidance and feedback provided
by labeled data, which can make it difficult to know whether the discovered patterns
are relevant or useful.
● Sensitivity to data quality: Unsupervised learning can be sensitive to data quality,
including missing values, outliers, and noisy data.
● Scalability: Unsupervised learning can be computationally expensive, particularly for
large datasets or complex algorithms, which can limit its scalability.

Supervised vs. Unsupervised Machine Learning:

Parameters Supervised machine learning Unsupervised machine learning

Algorithms are trained using labeled Algorithms are used against data
Input Data
data. that is not labeled

Computational
Simpler method Computationally complex
Complexity

Accuracy Highly accurate Less accurate

No. of classes No. of classes is known No. of classes is not known

Data Analysis Uses offline analysis Uses real-time analysis of data

Linear and Logistics regression,

K-Means clustering, Hierarchical
Algorithms Random forest,
clustering,
used Support Vector Machine, Neural
Apriori algorithm, etc.
Network, etc.

Output Desired output is given. Desired output is not given.

Training data Use training data to infer models. No training data is used.

Complex model It is not possible to learn larger and It is possible to learn larger and
 more complex models than with more complex models with
supervised learning. unsupervised learning.

Model We can test our model. We can not test our model.

Supervised learning is also called Unsupervised learning is also

Called as
classification. called clustering.

Example: Optical character

Example Example: Find a face in an image.
recognition.

Deep Learning vs. Neural Networks

The terms “neural network” and “deep learning” are often used interchangeably, but there are
some nuanced differences between the two. While both are subsets of machine learning, a neural
network mimics the way the biological neurons in the human brain work, while a deep learning
network comprises several layers of neural networks.
Here, we’ll define neural networks and deep learning networks in greater detail, highlight their
differences, and look at some examples of each in practice.

Deep Learning vs. Neural Networks: What’s the Difference?

A neural network is a form of machine learning that models the interconnected neurons of the
human brain.
In the human brain, each neuron interconnects with another neuron to receive information,
process it, and pass it to other neurons. In much the same way, neural networks receive
information in the input layer, process it through at least one hidden layer, and then pass the
result to the output layer. Therefore, in its simplest form, a neural network comprises an input
layer, a hidden layer, and an output layer.
Deep learning, on the other hand, is made up of several hidden layers of neural networks that
perform complex operations on massive amounts of structured and unstructured data. In contrast,
they identify patterns in real-world data such as images, text, sound, and time series, using
training data to improve the accuracy of their predictions.

How Does a Neural Network Work?

Neural networks can be trained to “think” and identify hidden relationships, patterns, and trends
in data, within context.
In the first step of the neural network process, the first layer receives the raw input data; then,
each consecutive layer receives the output from the preceding layer. Each layer contains a
database that stores all the network has previously learned, as well as programmed or interpreted
rules. Processing continues through each layer until the data reaches the output layer, which
produces the eventual result.
A neural network can be trained using supervised or unsupervised learning. Supervised learning
provides the network with the desired input and output algorithms, while unsupervised learning
allows the network to interpret the input and generate results without pre-programmed
instructions.

Few examples of a Neural Network for Deep Learning

The following are five examples of how neural networks can be used for deep learning:
1. Financial Predictions
In the financial industry, deep learning is used to make predictions on stock prices, currency,
options, and more. Applications use the past performance of stocks, non-profit ratios, and annual
returns as input to provide predictions that help financial executives make market predictions in
real time.
2. Autonomous Vehicles
Using data collected in real time from over 1 million vehicles, Tesla uses neural networks to help
autonomous vehicles navigate traffic lights and complex street networks to find an optimal route.
They use data from sensors, cameras, and radars to detect people, objects, and other vehicles in
the vehicle’s surroundings.
3. User Behavior Analysis
Neural networks process and analyze large volumes of content generated by users on social
media, websites, and mobile applications. The valuable insights derived from this process are
used to create targeted advertising campaigns based on user preference, activity, and purchase
history.

4. Disease Mapping
Neural networks are increasingly being used in healthcare to detect life-threatening illnesses like
cancer, manage chronic diseases, and detect abnormalities in medical imaging.
5. Criminal Surveillance
While its use remains controversial, some law enforcement officials use deep learning to detect
and prevent crimes. In these cases, convolutional neural networks use facial recognition
algorithms to match human faces against vast amounts of digital images to detect unusual
behavior, send alerts of suspicious activity, or identify known fugitives.

What Is a Deep Neural Network?

Deep learning, also a subset of machine learning, uses algorithms to recognize patterns in
complex data and predict outputs. Unlike machine learning algorithms, which require labeled
data sets, deep learning networks can be trained using unsupervised learning (which doesn’t
require labeled data sets) to perform feature extraction with less reliance on human input.
It’s called deep learning because of the number of hidden layers used in the deep learning model.
While a basic neural network comprises an input, output, and hidden layer, a deep neural
network has multiple hidden layers of processing.
These additional layers give deep learning systems the ability to make predictions with greater
accuracy, but they require millions of sample data points and hundreds of hours of training when
compared to a simpler neural network.

Neural Networks vs. Deep Neural Networks: What’s the Difference?

→ A deep neural network is a more complicated form of neural network. Where neural networks
give a single result such as a word, solution, or action, deep ones create a global solution based
on all the input data given.

→ Because of their multiple layers, a deep neural network takes longer to

train than a neural network, but they offer higher performance, efficiency,
and accuracy.
→ A neural network includes components such as neurons, connections,
propagation functions, learning rate, and weight. In contrast, a deep learning
network typically comprises a motherboard, processors (CPU or GPU), large
quantities of RAM, and a large power supply unit (PSU) for processing
complex deep learning functions and massive data sets.

→ Types of neural network architecture include feed-forward, recurrent, and

symmetrically connected neural networks, while deep learning types include
unsupervised pre-trained, convolutional, recurrent, and recursive neural
networks.

Why Do Neural Networks Run Faster on GPUs?

Neural networks require high throughput to process large amounts of data accurately in near real
time. Compared to CPUs, GPUs (Graphical Processing Units) offer higher memory bandwidth,
faster memory access, and the parallelism necessary to support the high-performance needs of a
neural network.

Parallelism allows them to complete multiple tasks at the same time. For example, a GPU can
process current matrix chunks while fetching more chunks from system memory, instead of
completing one task at a time as with a CPU.

This perfectly supports the neural network architecture because it allows tasks and workloads
with the same operations to be distributed across multiple GPU cores for faster, more efficient
processing.
Artificial neurons vs Biological neurons
The concept of artificial neural networks comes from biological neurons found in animal brains
So they share a lot of similarities in structure and function wise.
● Structure: The structure of artificial neural networks is inspired by biological
neurons. A biological neuron has a cell body or soma to process the impulses,
dendrites to receive them, and an axon that transfers them to other neurons. The input
nodes of artificial neural networks receive input signals, the hidden layer nodes
compute these input signals, and the output layer nodes compute the final output by
processing the hidden layer’s results using activation functions.

Biological Neuron Artificial Neuron

Dendrite Inputs

Cell nucleus or Soma Nodes

Synapses Weights

Axon Output

● Synapses: Synapses are the links between biological neurons that enable the
transmission of impulses from dendrites to the cell body. Synapses are the weights
that join the one-layer nodes to the next-layer nodes in artificial neurons. The strength
of the links is determined by the weight value.
● Learning: In biological neurons, learning happens in the cell body nucleus or soma,
which has a nucleus that helps to process the impulses. An action potential is
produced and travels through the axons if the impulses are powerful enough to reach
the threshold. This becomes possible by synaptic plasticity, which represents the
ability of synapses to become stronger or weaker over time in reaction to changes in
their activity. In artificial neural networks, backpropagation is a technique used for
learning, which adjusts the weights between nodes according to the error or
differences between predicted and actual outcomes.

Biological Neuron Artificial Neuron

Synaptic plasticity Backpropagations

● Activation: In biological neurons, activation is the firing rate of the neuron which
happens when the impulses are strong enough to reach the threshold. In artificial
neural networks, A mathematical function known as an activation function maps the
input to the output, and executes activations.
 Biological neurons to Artificial neurons

How do Artificial Neural Networks learn?

Artificial neural networks are trained using a training set. For example, suppose you want to
teach an ANN to recognize a cat. Then it is shown thousands of different images of cats so that
the network can learn to identify a cat. Once the neural network has been trained enough using
images of cats, then you need to check if it can identify cat images correctly. This is done by
making the ANN classify the images it is provided by deciding whether they are cat images or
not. The output obtained by the ANN is corroborated by a human-provided description of
whether the image is a cat image or not. If the ANN identifies incorrectly then back-propagation
is used to adjust whatever it has learned during training. Backpropagation is done by fine-tuning
the weights of the connections in ANN units based on the error rate obtained. This process
continues until the artificial neural network can correctly recognize a cat in an image with
minimal possible error rates.