UNIT-V-Syllabus

Bayesian Belief Network,

Concepts and mechanism,
Genetic Algorithms,
Reinforcement Learning
Active Learning
Transfer Learning,
Advance ML Applications

1
 Bayesian Belief Network

• Bayesian belief network is key computer technology for dealing with

probabilistic events and to solve a problem which has uncertainty.
• "A Bayesian network is a probabilistic graphical model which
represents a set of variables and their conditional dependencies
using a directed acyclic graph.“
• It is also called a Bayes network, belief network, decision network,
or Bayesian model.
• Bayesian networks are probabilistic, because these networks are built
from a probability distribution, and also use probability theory for
prediction and anomaly detection 2
 Bayesian Belief Network

• Real world applications are probabilistic in nature, and to

represent the relationship between multiple events, we need a
Bayesian network.
• It can also be used in various tasks including prediction, anomaly
detection, diagnostics, automated insight, reasoning, time series
prediction, and decision making under uncertainty.

It consists of two parts:

• Directed Acyclic Graph
• Table of conditional probabilities.
3
 Bayesian Belief Network

• A Bayesian network graph is made up of nodes and Arcs (directed

links)

The generalized form of Bayesian network that represents and solve decision
problems under uncertain knowledge is known as an Influence diagram.
4
 Bayesian Belief Network

• Each node corresponds to the random variables, and a variable can be continuous
or discrete.
• Arc or directed arrows represent the causal relationship or conditional probabilities
between random variables. These directed links or arrows connect the pair of nodes
in the graph.
• These links represent that one node directly influence the other node, and if there is
no directed link that means that nodes are independent with each other

5
 Bayesian Belief Network

• In the above diagram, A, B, C, and D are random variables represented by the nodes
of the network graph.
• If we are considering node B, which is connected with node A by a directed arrow,
then node A is called the parent of Node B.
• Node C is independent of node A.
• The Bayesian network graph does not contain any cyclic graph. Hence, it is known as a
directed acyclic graph or DAG 6
 Bayesian Belief Network

• In the above diagram, A, B, C, and D are random variables represented by the nodes
of the network graph.
• If we are considering node B, which is connected with node A by a directed arrow,
then node A is called the parent of Node B.
• Node C is independent of node A.
• The Bayesian network graph does not contain any cyclic graph. Hence, it is known as a
directed acyclic graph or DAG 7
Bayesian network is based on Joint probability distribution and conditional probability

Probability Basics

8
 Bayesian Belief Network

Joint Probability
• Joint probability is the likelihood of more than one event
occurring at the same time P(A and B).
• The probability of event A and event B occurring together.
It is the probability of the intersection of two or more events
written as p(A ∩ B).
Example: The probability that a card is a four and red =p(four
and red) = 2/52=1/26.
(There are two red fours in a deck of 52, the 4 of hearts and the
4 of diamonds).

9
 Bayesian Belief Network
Example: Harry installed a new burglar alarm at his home to
detect burglary.
• The alarm reliably responds at detecting a burglary but also
responds for minor earthquakes.
• Harry has 2 neighbors David &Sophia, who have taken a
responsibility to inform Harry at work when they hear the alarm
• David always calls Harry when he hears the alarm, but
sometimes he got confused with the phone ringing and calls a
that time too.
• On the other hand, Sophia likes to listen to high music, so
sometimes she misses to hear the alarm.
• Here we would like to compute the probability of Burglary
Alarm. 10
 Bayesian Belief Network

Problem: Calculate the probability that alarm has sounded, but

there is neither a burglary, nor an earthquake occurred, and
David and Sophia both called the Harry.

11
 Bayesian Belief Network

List of all events occurring in this network:

• Burglary (B)
• Earthquake(E)
• Alarm(A)
• David Calls(D)
• Sophia calls(S)

12
 Bayesian Belief Network
We can write the events of problem statement in the form of
probability: P[D, S, A, B, E], can rewrite the above probability
statement using joint probability distribution:

P[D, S, A, B, E]= P[D | S, A, B, E]. P[S, A, B, E]

=P[D | S, A, B, E]. P[S | A, B, E]. P[A, B, E]

= P [D| A]. P [ S| A, B, E]. P[ A, B, E]

= P[D | A]. P[ S | A]. P[A| B, E]. P[B, E]

= P[D | A ]. P[S | A]. P[A| B, E]. P[B |E]. P[E] 13

Bayesian Belief Network

14
 Bayesian Belief Network

Let's take the observed probability for the Burglary and

earthquake component:

P(B= True) = 0.002, which is the probability of burglary.

P(B= False)= 0.998, which is the probability of no burglary.

P(E= True)= 0.001, which is the probability of a minor earthquake

P(E= False)= 0.999, Which is the probability that an earthquake not

occurred.

15
 Bayesian Belief Network

Conditional probability table for Alarm A:

The Conditional probability of Alarm A depends on Burglar and

earthquake:

B E P(A= True) P(A= False)

True True 0.94 0.06
True False 0.95 0.04
False True 0.31 0.69
False False 0.001 0.999

16
 Bayesian Belief Network

Conditional probability table for David Calls:

The Conditional probability of David that he will call depends on the

probability of Alarm.

A P(D= True) P(D= False)

True 0.91 0.09
False 0.05 0.95

17
 Bayesian Belief Network

Conditional probability table for Sophia Calls:

The Conditional probability of Sophia that she calls is depending on

its Parent Node "Alarm."

A P(S= True) P(S= False)

True 0.75 0.25
False 0.02 0.98

18
 Bayesian Belief Network

From the formula of joint distribution, we can write the problem

statement in the form of probability distribution:

P(S, D, A, ¬B, ¬E) = P (S|A) *P (D|A)*P (A|¬B ^ ¬E) *P (¬B) *P (¬E).

= 0.75* 0.91* 0.001* 0.998*0.999

= 0.00068045.

Hence, a Bayesian network can answer any query about the domain by
using Joint distribution.

19
 Active Learning
•Understanding passive/active learning
•Introduction to active learning
•Why active learning and its significance
•Active learning basic architecture/life cycle
•Active learning strategy and its working
•Use cases for active learning

20
 Understanding Passive Learning
■Passive learning, the standard framework in which a
large quantity of labelled data is passed to the
algorithm, requires significant effort in labelling the
entire set of data.

21
 Understanding Active Learning
■By using active learning, we can selectively leverage a system like crowd-
sourcing, to ask human experts to selectively label some items in the data set,
but not have to label the entirety.
■The algorithm iteratively selects the most informative examples based on some
value metric and sends those unlabelled examples to a labelling oracle, who
returns the true labels for those queried examples back to the algorithm.

22
 Introduction: Active Learning
■ The primary goal of machine learning is to derive general patterns from a
limited amount of data.
■ For most of supervised and unsupervised learning tasks, what we usually do is
to gather a significant quantity of data which is randomly sampled from the
underlying population distribution and then we induce a classifier or model.
■ But this process is some kind of passive!
■ Often the most time-consuming and costly task in the process is the gathering
the data.
■ Example: document classification.
■ Easy to get large pool of unlabeled document, but it will take a long time for
people to hand-label thousands of training document.

23
 Introduction: Active Learning
■ Now, instead of randomly picking documents to
be manually labeled fro our training set, we want
to choose and query documents from the pool
very carefully.
■ Based on this carefully choosing training data, we
can improve the model’s performance very
quickly.
24
 Introduction: Active Learning
■ Active learning is the subset of machine learning in which a
learning algorithm can query a user interactively to label data
with the desired outputs.
■ A growing problem in machine learning is the large amount of
unlabeled data, since data is continuously getting cheaper to
collect and store.
■ Active learning is the subset of machine learning in which a
learning algorithm can query a user interactively to label data
with the desired outputs. In active learning, the algorithm
proactively selects the subset of examples to be labeled next
from the pool of unlabeled data.
25
 Introduction: Active Learning
■ The fundamental belief behind the active learner algorithm concept is
that an ML algorithm could potentially reach a higher level of accuracy
while using a smaller number of training labels if it were allowed to
choose the data it wants to learn from.
■ Therefore, active learners are allowed to interactively pose queries
during the training stage.
■ These queries are usually in the form of unlabeled data instances and
the request is to a human annotator to label the instance.
■ This makes active learning part of the human-in-the-loop paradigm,
where it is one of the most powerful examples of success.

26
 Why Active Learning?
■Most supervised machine learning models require large amounts of data
to be trained with good results. And even if this statement sounds naive,
most companies struggle to provide their data scientists this data, in
particular labelled data. The latter is key to train any supervised model
and can become the main bottleneck for any data team.

■In most cases, data scientists are provided with a big, unlabelled data
sets and are asked to train well-performing models with them. Generally,
the amount of data is too large to manually label it, and it becomes quite
challenging for data teams to train good supervised models with that
data.

27
 Significance of Active Learning
■ Active Learning is a “human-in-the-loop” type of Deep Learning
framework that uses a large dataset of which only a small
portion (say 10%) is labeled for model training. Say there is a
dataset of 1,000 samples, of which 100 are labeled. An Active
Learning-based model will train on the 100 samples and make
predictions on the rest of the 900 samples (test set). Suppose, of
these 900 samples, the confidence in prediction was very low for
10 samples. The model will now ask a human user to provide it
with the labels for these 10 samples. That is, an Active Learning
framework is interactive, and that’s how the name “Active” was
coined.

28
Active Learning: Basic Architecture

29
 Active Learning Cycle

Because an active learning approach starts with a small labeled dataset, the initial
predictions that the model makes on the unlabeled data won’t be very. However, this
iterative training, testing, identifying uncertainty, annotating, and retraining feedback loop
continues until the model reaches an acceptable performance threshold. At that point, the
model’s predictions with a high level of certainty can be sent downstream for use in
production while the others are sent back to the annotators, keeping the loop active and
constantly improving. 30
 Active Learning: Motivation
■Active learning is the name used for the process of prioritising the data which needs to be
labelled in order to have the highest impact to training a supervised model.
■Active learning can be used in situations where the amount of data is too large to be labelled and
some priority needs to be made to label the data in a smart way.
■Active learning is closer to traditional supervised learning, a type of semi-supervised learning,
meaning models are trained using both labeled and unlabeled data.
■The idea behind semi-supervised learning is that labeling just a small sample of data might result
in the same accuracy or better than fully labeled training data.
■The only challenge is determining what that sample is: Active learning machine learning is all
about labeling data dynamically and incrementally during the training phase so that the algorithm
can identify what label would be the most beneficial for it to learn from.

31
 Active Learning Strategy
■Steps for active learning
■There are multiple approaches studied in the literature on how to prioritise data
points when labelling and how to iterate over the approach.
■We will nevertheless only present the most common and straightforward
methods.
■The steps to use active learning on an unlabelled data set are:
■The first thing which needs to happen is that a very small subsample of this data
needs to be manually labelled.
■Once there is a small amount of labelled data, the model needs to be trained on
it.
■The model is of course not going to be great but will help us get some insight on
which areas of the parameter space need to be labelled first to improve it.

32
 Active Learning Strategy
■After the model is trained, the model is used to predict the class of each
remaining unlabelled data point.
■A score is chosen on each unlabelled data point based on the prediction of the
model.
■Once the best approach has been chosen to prioritise the labelling, this process
can be iteratively repeated: a new model can be trained on a new labelled data
set, which has been labelled based on the priority score.
■Once the new model has been trained on the subset of data, the unlabelled data
points can be ran through the model to update the prioritisation scores to
continue labelling.
■In this way, one can keep optimising the labelling strategy as the models become
better and better.

33
 How does Active Learning work?
■ Active learning works in a few different situations, basically, the
decision of whether or not to query each specific label depends
on whether the gain from querying the label is greater than the
cost of obtaining that information.
■ This decision making, in practice, can take a few different forms
based on the data scientist’s budget limit and other factors.
■ The three categories of active learning are:
■Stream based selective sampling
■Pool-based sampling
■Membership query synthesis
34
 How does Active Learning work?
■ Stream-based selective sampling
■ In this scenario, the algorithm determines if it would be
beneficial enough to query for the label of a specific
unlabeled entry in the dataset.
■ While the model is being trained, it is presented with a
data instance and immediately decides if it wants to query
the label.
■ This approach has a natural disadvantage that comes from
the lack of guarantee that the data scientist will stay
within budget.
35
 How does Active Learning work?
■ Pool-based sampling
■ This is the most well known scenario for active learning.
■ In this sampling method, the algorithm attempts to evaluate the
entire dataset before it selects the best query or set of queries.
■ The active learner algorithm is often initially trained on a fully labeled
part of the data which is then used to determine which instances
would be most beneficial to insert into the training set for the next
active learning loop.
■ The downside of this method is the amount of memory it can require.

36
 How does Active Learning work?
■ Membership query synthesis
■ This scenario is not applicable to all cases, because it
involves the generation of synthetic data.
■ The active learner in this method is allowed to create
its own examples for labeling.
■ This method is compatible with problems where it is
easy to generate a data instance.
37
 Active Learning Use Cases
■ Active learning has found a number of applications in areas such as text categorization,
document classification, and image recognition. It has also been used for cancer detection
and drug discovery.
■ Text Categorization
■ One of the most common applications of active learning is text categorization, which is the task
of assigning a category to a piece of text. In this application, the categories are usually a set of
predefined labels such as “news”, “sports”, “entertainment”, and “opinion”. The goal is to
automatically assign each piece of text to one of these categories.
■ Document Classification
■ Active learning can also be used for document classification, which is the task of automatically
assigning a class to a document. In this application, the classes are usually a set of predefined
labels such as “technical document”, “marketing document”, and “legal document”.

38
 Active Learning Use Cases
■ Image Recognition
■ Image recognition is another area where active learning can be used. In
this example, we have an image and we’d like our annotators to label only
relevant regions in the image. In other words, we need to make sure that
each labeled region contributes maximum information for classifying the
image. To achieve this objective, active learning will pick up the most
interesting regions from unlabelled data and let them be processed by
annotators.
■ This way, annotators don’t waste any time on labeling redundant
parts of an image that would have remained untagged if they were
just blindly assigning labels to all regions in an image.

39
 Reinf Reinforcement learning
orcement Learning

•Reinforcement learning is an area of Machine Learning.

•It is about taking suitable action to maximize reward in a particular
situation.
• It is employed by various software and machines to find the best
possible behavior or path it should take in a specific situation.
• Reinforcement learning differs from supervised learning in a way
that in supervised learning the training data has the answer key with
it so the model is trained with the correct answer itself whereas in
reinforcement learning, there is no answer but the reinforcement
agent decides what to do to perform the given task.
•In the absence of a training dataset, it is bound to learn from its
experience.

40
•Reinforcement Learning (RL) is the science of decision
making.
•It is about learning the optimal behavior in an
environment to obtain maximum reward.
•In RL, the data is accumulated from machine learning
systems that use a trial-and-error method.
•Data is not part of the input that we would find in
supervised or unsupervised machine learning.

41
○ Reinforcement Learning is a feedback-based Machine
learning technique in which an agent learns to behave in an
environment by performing the actions and seeing the results
of actions. For each good action, the agent gets positive
feedback, and for each bad action, the agent gets negative
feedback or penalty.
○ In Reinforcement Learning, the agent learns automatically using
feedbacks without any labeled data, unlike supervised learning.
○ Since there is no labeled data, so the agent is bound to learn by its
experience only.
42
43
•Reinforcement learning uses algorithms that learn from
outcomes and decide which action to take next.
•After each action, the algorithm receives feedback that helps it
determine whether the choice it made was correct, neutral or
incorrect.
•It is a good technique to use for automated systems that have
to make a lot of small decisions without human guidance.
•Reinforcement learning is an autonomous, self- teaching
system that essentially learns by trial and error.
•It performs actions with the aim of maximizing rewards, or in
other words, it is learning by doing in order to achieve the best
outcomes.
44
 Elements of
Reinforcement Learning

1. Policy
2. Reward function
3. Value function
4. Model of the environment

45
Policy: Policy defines the learning agent behavior for given
time period. It is a mapping from perceived states of the
environment to actions to be taken when in those states.
Reward function: Reward function is used to define a goal
in a reinforcement learning problem.A reward function is a
function that provides a numerical score based on the state
of the environment
Value function: Value functions specify what is good in the
long run. The value of a state is the total amount of reward
an agent can expect to accumulate over the future, starting
from that state.
46
Model of the environment: Models are used for
planning.

The reinforcement learning problem model is an

agent continuously interacting with an environment.
The agent and the environment interact in a
sequence of time steps. At each time step t, the
agent receives the state of the environment and a
scalar numerical reward for the previous action, and
then the agent then selects an action.

47
•Example: 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.

48
49
•The 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.

50
 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.

51
52
 Application of Reinforcement Learnings

1. Robotics: Robots with pre-programmed behavior are useful

in structured environments, such as the assembly line of an
automobile manufacturing plant, where the task is repetitive in
nature.
2. A master chess player makes a move. The choice is
informed both by planning, anticipating possible replies and
counter replies.
3. An adaptive controller adjusts parameters of a petroleum
refinery’s operation in real time.

53
 Advantages of Reinforcement learning

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.
54
 Disadvantages of Reinforcement learning

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.

55
Genetic algorithms

56
 History of GAs

■ As early as 1962, John Holland's work on adaptive

systems laid the foundation for later developments.
■ By the 1975, the publication of the book Adaptation
in Natural and Artificial Systems, by Holland and his
students and colleagues

57
■ early to mid-1980s, genetic algorithms were being
applied to a broad range of subjects.
■ In 1992 John Koza has used genetic algorithm to
evolve programs to perform certain tasks. He called
his method "genetic programming" (GP).

58
 What is GA

■ A genetic algorithm (or GA) is a search technique

used in computing to find true or approximate
solutions to optimization and search problems.
■ (GA)s are categorized as global search heuristics.
■ (GA)s are a particular class of evolutionary algorithms
that use techniques inspired by evolutionary biology
such as inheritance, mutation, selection, and
crossover (also called recombination)

59
■ The evolution usually starts from a population of
randomly generated individuals and happens in
generations. •

■ In each generation, the fitness of every individual in

the population is evaluated, multiple individuals are
selected from the current population (based on their
fitness), and modified to form a new population

60
■ The new population is used in the next iteration of
the algorithm. •
■ The algorithm terminates when either a maximum
number of generations has been produced, or a
satisfactory fitness level has been reached for the
population.

61
 Vocabulary

■ Individual - Any possible solution •

■ Population - Group of all individuals •
■ Fitness – Target function that we are optimizing
(each individual has a fitness) •
■ Trait - Possible aspect (features) of an individual •
Genome - Collection of all chromosomes (traits) for
an individual

62
 Basic Genetic Algorithm

■ Start with a large “population” of randomly

generated “attempted solutions” to a problem •
■ Repeatedly do the following: – Evaluate each of the
attempted solutions – (probabilistically) keep a
subset of the best solutions – Use these solutions to
generate a new population •
■ Quit when you have a satisfactory solution (or you
run out of time

63
 Example: the MAXONE
problem

■ Suppose we want to maximize the number of ones in

a string of l binary digits
■ It may seem so because we know the answer in
advance
■ However, we can think of it as maximizing the
number of correct answers, each encoded by 1, to l
yes/no difficult questions

64
 Example (cont)

■ An individual is encoded (naturally) as a string of l

binary digits •
■ The fitness f of a candidate solution to the MAXONE
problem is the number of ones in its genetic code •
■ We start with a population of n random strings.
Suppose that l = 10 and n = 6

65
Example (initialization)

66
67
68
 Step 2: crossover

■ Next we mate strings for crossover. For each couple

we first decide (using some pre-defined probability,
for instance 0.6) whether to actually perform the
crossover or not •
■ If we decide to actually perform crossover, we
randomly extract the crossover points, for instance 2
and 5

69
70
71
 And now, iterate …

■ In one generation, the total population fitness

changed from 34 to 37, thus improved by ~9%
■ At this point, we go through the same process all
over again, until a stopping criterion is met

72
 GA Operators

■ Methods of representation •
■ Methods of selection •
■ Methods of Reproduction

73
 Common representation
methods

■ Binary strings. •
■ Arrays of integers (usually bound) •
■ Arrays of letters

74
 Methods of Selection

There are many different strategies to select the

individuals to be copied over into the next generation

75
 Methods of Selection

Roulette-wheel selection. •
Elitist selection. •
Fitness-proportionate selection. •
Scaling selection. •
Rank selection.

76
Roulette wheel selection
-Conceptually, this can be represented as a game of
roulette - each individual gets a slice of the wheel, but
more fit ones get larger slices than less fit ones.

77
 Methods of Reproduction

There are primary methods:

–Crossover
–Mutation

78
 Methods of Reproduction: Crossover

Two parents produce two offspring –

Two options:
1. The chromosomes of the two parents are copied to
the next generation
2. The two parents are randomly recombined (crossed-
over) to form new offsprings

79
80
81
 Benefits of Genetic
Algorithms

■ Concept is easy to understand •

■ Modular, separate from application •
■ Supports multi-objective optimization •
■ Always an answer; answer gets better with time. •
■ Easy to exploit previous or alternate solutions •
■ Flexible building blocks for hybrid applications.

82
83
 Introduction to Transfer
Learning in ML
■ Humans are extremely skilled at transferring knowledge from one task to another.
■ This means that when we face a new problem or task, we immediately recognize
it and use the relevant knowledge we have gained from previous learning
experiences.
■ This makes it easy to complete our tasks quickly and efficiently.
■ If a user can ride a bike and are asked to drive a motorbike, this is a good
example. Their experience with riding a bike will be helpful in such situations.
They can balance the bike and steer the motorbike.
■ This will make it easier than if they were a complete beginner. These lessons
are extremely useful in real life because they make us better and allow us to
gain more experience.
■ The same approach was used to introduce Transfer learning into machine
learning. This involves using knowledge from a task to solve a problem in the
target task.
■ Although most machine learning algorithms are designed for a single task, there is
an ongoing interest in developing transfer learning algorithms.
 Why Transfer Learning?

■ One curious feature that many deep neural networks

built on images share is the ability to detect edges,
colours, intensities variations, and other features in the
early layers.
■ These features are not specific to any particular task or
dataset.
■ It doesn't matter what kind of image we are using to
detect lions or cars.
■ These low-level features must be detected in both cases.
These features are present regardless of whether the
image data or cost function is exact.
■ These features can be learned in one task, such as
detecting lions. They can also be used to detect humans.
Transfer learning is exactly what this is.
Block Diagram
 Freezed and Trainable Layers:

■ The freezing of layers characterizes transfer learning.

When a layer is unavailable to train, it is called a
"Frozen Layer". It can be either a CNN layer or a
hidden layer. Layers that have not been frozen are
subject to regular training. Training will not update
the layers' weights that have been frozen.
Let's look at all scenarios where the target task size and data set differ
from the base network.
■ The target dataset is smaller than the base network data: Because
the target dataset is so small, we can fine-tune our pre-trained
network using this target dataset. This could lead to overfitting. There
may also be changes in the number of classes for the target task. In
such cases, we may need to remove some layers that are not fully
connected from the end and add a new layer that is fully connected.
We now freeze the rest of our model and train only newly added
layers.
■ The target dataset is large, similar to the base training dataset: If the
dataset is large enough to hold a pre-trained model, there won't be
any chance of overfitting. This is where the last fully connected layer
is removed, and a new fully connected layer with the correct number
of classes is added. The entire model is now trained on a new dataset.
This allows the model to be tuned on a large new dataset while
keeping the architecture unchanged.
■ The target dataset is smaller than the base network
data, and therefore, it is different: The target dataset is
unique, so pre-trained models with high-level features
will not work. We can remove the most layers from the
end of a pre-trained model and add layers that satisfy the
number of classes in the new dataset. We can then use
the low-level features of the pre-trained model to train
the remaining layers to adapt to a new dataset.
Sometimes it can be beneficial to train the entire
network, even after adding a layer at the end.
■ The target dataset is larger than the base network
data: As the target network is complex and diverse, it is
best to remove layers from pre-trained networks and add
layers that satisfy a number of classes. Then train the
entire network without freezing any layers.
 Examples of transfer learning for
machine learning

■ Although an emerging technique, transfer learning is

already being utilised in a range of fields within
machine learning. Whether strengthening natural
language processing or computer vision, transfer
learning already has a range of real-world usage.
■ Examples of the areas of machine learning that utilise
transfer learning include:
■ Natural language processing
■ Computer vision
■ Neural networks
 Transfer learning in
natural language processing

■ Natural language processing is the ability of a system to understand and

analyze human language, whether through audio or text files. It’s an
important part of improving how humans and systems interact. Natural
language processing is intrinsic to everyday services like voice assistants,
speech recognition software, automated captions, translations, and language
contextualization tools.
■ Transfer learning is used in a range of ways to strengthen machine learning
models that deal with natural language processing. Examples include
simultaneously training a model to detect different elements of language, or
embedding pre-trained layers which understand specific dialects or
vocabulary.
■ Transfer learning can also be used to adapt models across different
languages. Aspects of models trained and refined based on the English
language can be adapted for similar languages or tasks. Digitized English
language resources are very common, so models can be trained on a large
dataset before elements are transferred to a model for a new language.
 Transfer learning in
computer vision
■ Computer vision is the ability of systems to understand and
take meaning from visual formats such as videos or images.
Machine learning algorithms are trained on huge collections
of images to be able to recognise and categorise image
subjects. Transfer learning in this case will take the reusable
aspects of a computer vision algorithm and apply it to a new
model.
■ Transfer learning can take the accurate models produced
from large training datasets and help apply it to smaller sets
of images. This includes transferring the more general aspects
of the model, such as the process for identifying the edges of
objects in images. The more specific layer of the model which
deals with identifying types of objects or shapes can then be
trained. The model’s parameters will need to be refined and
optimised, but the core functionality of the model will have
been set through transfer learning.
 Transfer learning in neural
networks
■ Artificial neural networks are an important aspect of
deep learning, an area of machine learning attempting to
simulate and replicate the functions of the human brain.
The training of neural networks takes a huge amount of
resources because of the complexity of the models.
Transfer learning is used to make the process more
efficient and lower the resource demand.
■ Any transferable knowledge or features can be moved
between networks to streamline the development of
new models. The application of knowledge across
different tasks or environments is an important part of
building such a network. Transferred learning will usually
be limited to general processes or tasks which stay viable
in different environments.
 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:

■ 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.
 Applications of
Machine learning

■ We are using machine

learning in our daily
life even without
knowing it such as
Google Maps, Google
assistant, Alexa, etc.
Below are some most
trending real-world
applications of
Machine Learning.
 1. Image Recognition:

■ Image recognition is one of the most common

applications of machine learning. It is used to identify
objects, persons, places, digital images, etc. The popular
use case of image recognition and face detection
is, Automatic friend tagging suggestion:
■ Facebook provides us a feature of auto friend tagging
suggestion. Whenever we upload a photo with our
Facebook friends, then we automatically get a tagging
suggestion with name, and the technology behind this is
machine learning's face detection and recognition
algorithm.
■ It is based on the Facebook project named "Deep Face,"
which is responsible for face recognition and person
identification in the picture.
 2. Speech Recognition

■ While using Google, we get an option of "Search by

voice," it comes under speech recognition, and it's a
popular application of machine learning.
■ Speech recognition is a process of converting voice
instructions into text, and it is also known as "Speech
to text", or "Computer speech recognition." At
present, machine learning algorithms are widely used
by various applications of speech recognition. Google
assistant, Siri, Cortana, and Alexa are using speech
recognition technology to follow the voice
instructions.
 3. Traffic prediction:

■ If we want to visit a new place, we take help of Google

Maps, which shows us the correct path with the shortest
route and predicts the traffic conditions.
■ It predicts the traffic conditions such as whether traffic is
cleared, slow-moving, or heavily congested with the help
of two ways:
■ Real Time location of the vehicle form Google Map app and
sensors
■ Average time has taken on past days at the same time.
■ Everyone who is using Google Map is helping this app to
make it better. It takes information from the user and
sends back to its database to improve the performance.
 4. Product recommendations:

■ Machine learning is widely used by various e-commerce

and entertainment companies such as Amazon, Netflix,
etc., for product recommendation to the user. Whenever
we search for some product on Amazon, then we started
getting an advertisement for the same product while
internet surfing on the same browser and this is because
of machine learning.
■ Google understands the user interest using various
machine learning algorithms and suggests the product as
per customer interest.
■ As similar, when we use Netflix, we find some
recommendations for entertainment series, movies, etc.,
and this is also done with the help of machine learning.
 5. Self-driving cars:

■ One of the most exciting applications of machine

learning is self-driving cars. Machine learning plays a
significant role in self-driving cars. Tesla, the most
popular car manufacturing company is working on
self-driving car. It is using unsupervised learning
method to train the car models to detect people and
objects while driving.
 6. Virtual Personal Assistant:

■ We have various virtual personal assistants such

as Google assistant, Alexa, Cortana, Siri. As the
name suggests, they help us in finding the
information using our voice instruction. These
assistants can help us in various ways just by our
voice instructions such as Play music, call someone,
Open an email, Scheduling an appointment, etc.
■ These virtual assistants use machine learning
algorithms as an important part.
■ These assistant record our voice instructions, send it
over the server on a cloud, and decode it using ML
algorithms and act accordingly.
 7. Medical Diagnosis:

■ In medical science, machine learning is used for

diseases diagnoses. With this, medical technology is
growing very fast and able to build 3D models that
can predict the exact position of lesions in the brain.
■ It helps in finding brain tumors and other brain-
related diseases easily.
 8. Automatic Language
Translation:
■ Nowadays, if we visit a new place and we are not
aware of the language then it is not a problem at all,
as for this also machine learning helps us by
converting the text into our known languages.
Google's GNMT (Google Neural Machine Translation)
provide this feature, which is a Neural Machine
Learning that translates the text into our familiar
language, and it called as automatic translation.
■ The technology behind the automatic translation is a
sequence to sequence learning algorithm, which is
used with image recognition and translates the text
from one language to another language.
Thank You

105