What is AI (Artificial Intelligence):

Artificial Intelligence (AI) is a branch of computer science that focuses

on creating machines or software that can think, learn, and perform
tasks that typically require human intelligence. AI enables computers
to solve problems, recognize patterns, make decisions, and even
understand natural language.
Some of the examples of statistical techniques that are used for
developing AI applications and are still in practice are listed here:
 Regression
 Classification
 Clustering
 Probability Theories
 Decision Trees
If you are developing AI applications based on limited data, you
would be using these statistical techniques. However, today the data
is abundant. To analyze the kind of huge data that we possess
statistical techniques are of not much help as they have some
limitations of their own. More advanced methods such as deep
learning are hence developed to solve many complex problems.
Examples of AI
Chatbots (like ChatGPT) – AI-powered assistants that can answer
questions, provide recommendations, and have conversations.
Face Recognition (Face ID) – AI helps recognize and verify faces for
security purposes in smartphones and surveillance systems.
Google Search & Recommendations – AI helps Google suggest
search results, YouTube recommends videos, and Netflix suggests
movies based on user preferences.
 Self-Driving Cars – AI allows cars to detect obstacles, follow traffic
rules, and drive without human intervention.
What is Machine Learning?
Machine Learning (ML) is a branch of artificial intelligence (AI) that
enables computers to learn from data and make decisions without
being explicitly programmed. Instead of following fixed rules, ML
algorithms identify patterns in data and improve their performance
over time.
Consider the following figure that shows a plot of house prices versus
its size in sq. ft.

After plotting various data points on the XY plot, we draw a best-fit

line to do our predictions for any other house given its size. You will
feed the known data to the machine and ask it to find the best fit
line. Once the best fit line is found by the machine, you will test its
suitability by feeding in a known house size, i.e. the Y-value in the
above curve. The machine will now return the estimated X-value, i.e.
the expected price of the house. The diagram can be extrapolated to
find out the price of a house which is 3000 sq. ft. or even larger. This
is called regression in statistics. Particularly, this kind of regression is
called linear regression as the relationship between X & Y data points
is linear.
In many cases, the relationship between the X & Y data points may
not be a straight line, and it may be a curve with a complex equation.
Your task would be now to find out the best fitting curve which can
be extrapolated to predict the future values. One such application
plot is shown in the figure below.

You will use the statistical optimization techniques to find out the
equation for the best fit curve here. And this is what exactly Machine
Learning is about. You use known optimization techniques to find the
best solution to your problem.
Example of Machine Learning
Spam Email Detection
Email services like Gmail use machine learning to automatically
detect spam emails. The ML model analyzes past emails marked as
spam and learns patterns like specific words, sender addresses, and
message formats. When a new email arrives, the model predicts
whether it is spam or not.
Self-Driving Cars
Self-driving cars use ML to recognize traffic signs, pedestrians, and
other vehicles. By learning from thousands of driving scenarios, the
system makes decisions like stopping at red lights and changing lanes
safely.
Voice Assistants (Siri, Alexa, Google Assistant)
These assistants use ML to understand speech, recognize commands,
and improve responses over time based on user interactions.

Difference Between AI and Machine Learning

Artificial Intelligence
Feature Machine Learning (ML)
(AI)
AI is a broad field that ML is a subset of AI that
enables machines to focuses on training machines
Definition
mimic human to learn from data and
intelligence. improve automatically.
To create smart To develop algorithms that can
Goal systems that can think learn from data and make
and act like humans. predictions.
Includes ML, deep
A specific AI technique that
learning, robotics,
allows machines to learn from
Scope natural language
data without explicit
processing (NLP), and
programming.
more.
Example AI-powered chatbots, Email spam detection,
self-driving cars, and recommendation systems, and
 Artificial Intelligence
Feature Machine Learning (ML)
(AI)
robotics. facial recognition.
Does it No, some AI systems
Yes, ML always learns from
always learn are rule-based (e.g.,
data to improve accuracy.
from data? expert systems).

Simple Analogy
 AI is like a teacher who knows everything and can solve
different problems.
 ML is like a student who learns from examples and improves
over time.
 Lecturer -2
Machine Learning – Categories of Machine Learning

Machine learning evolved from left to right as shown in the above

diagram.
 Initially, researchers started out with Supervised Learning. This
is the case of housing price prediction discussed earlier.
 This was followed by unsupervised learning, where the machine
is made to learn on its own without any supervision.
 Scientists discovered further that it may be a good idea to
reward the machine when it does the job the expected way and
there came the Reinforcement Learning.
 Very soon, the data that is available these days has become so
humongous that the conventional techniques developed so far
failed to analyze the big data and provide us the predictions.
 Thus, came the deep learning where the human brain is
simulated in the Artificial Neural Networks (ANN) created in our
binary computers.
 The machine now learns on its own using the high computing
power and huge memory resources that are available today.
 It is now observed that Deep Learning has solved many of the
previously unsolvable problems.
 The technique is now further advanced by giving incentives to
Deep Learning networks as awards and there finally comes
Deep Reinforcement Learning.
Supervised Learning

Definition: Supervised Learning is a type of machine learning

where a model is trained using labeled data. This means the
dataset contains input-output pairs, where the correct answer
(label) is already known. The model learns from these examples
and can later make predictions on new, unseen data.
How It Works:
1. Training Phase – The model is given input data (features) along
with the correct output (label).
2. Learning Process – The model finds patterns and relationships
between inputs and outputs.
3. Prediction – After training, the model can predict outputs for
new inputs.
4. Evaluation – The model's performance is tested using a
separate dataset.

Example:
 Supervised learning is analogous to training a child to
walk. You will hold the child’s hand, show him how to
take his foot forward, walk yourself for a demonstration
and so on, until the child learns to walk on his own.
 Email Spam Detection – Emails are labeled as "spam" or
"not spam," and the model learns to classify new emails.
  Medical Diagnosis – A model is trained on patient records
to predict diseases.

Supervised learning is used in applications like speech

recognition, fraud detection, and recommendation
systems

Some technique is used in Supervised Learning

Regression :

 Similarly, in the case of supervised learning, you give concrete

known examples to the computer. You say that for given
feature value x1 the output is y1, for x2 it is y2, for x3 it is y3,
and so on. Based on this data, you let the computer figure out
an empirical relationship between x and y.
 Once the machine is trained in this way with a sufficient
number of data points, now you would ask the machine to
predict Y for a given X. Assuming that you know the real value
of Y for this given X, you will be able to deduce whether the
machine’s prediction is correct.
 Thus, you will test whether the machine has learned by using
the known test data. Once you are satisfied that the machine is
able to do the predictions with a desired level of accuracy (say
80 to 90%) you can stop further training the machine.
 Now, you can safely use the machine to do the predictions on
unknown data points, or ask the machine to predict Y for a
given X for which you do not know the real value of Y. This
training comes under the regression that we talked about
earlier.

Classification

 You may also use machine learning techniques for classification

problems. In classification problems, you classify objects of
 similar nature into a single group. For example, in a set of 100
students say, you may like to group them into three groups
based on their heights - short, medium and long. Measuring the
height of each student, you will place them in a proper group.
 Now, when a new student comes in, you will put him in an
appropriate group by measuring his height. By following the
principles in regression training, you will train the machine to
classify a student based on his feature – the height. When the
machine learns how the groups are formed, it will be able to
classify any unknown new student correctly. Once again, you
would use the test data to verify that the machine has learned
your technique of classification before putting the developed
model in production.

Unsupervised Learning

Definition: Unsupervised learning is a type of machine learning

where the algorithm learns patterns and structures from data
without labeled examples. Unlike supervised learning, where
the model is trained using labeled input-output pairs,
unsupervised learning finds hidden patterns, similarities, or
groupings in the data on its own.

How it works:

1. Input Data Collection – The algorithm is given a dataset without

labels (only raw data).
2. Pattern Identification – The model searches for similarities,
correlations, or structures in the data.
3. Grouping or Transformation – Based on patterns, the algorithm
clusters or transforms the data into meaningful structures.
4. Interpretation – The output is analyzed and used for decision-
making, such as grouping customers based on purchasing
behavior.

In unsupervised learning, we do not specify a target variable to

the machine, rather we ask machine “What can you tell me
about X?”. More specifically, we may ask questions such as
given a huge data set X, “What are the five best groups we can
make out of X?” or “What features occur together most
frequently in X?”. To arrive at the answers to such questions,
you can understand that the number of data points that the
machine would require to deduce a strategy would be very
large. In case of supervised learning, the machine can be
trained with even about few thousands of data points.
However, in case of unsupervised learning, the number of data
points that is reasonably accepted for learning starts in a few
millions. These days, the data is generally abundantly available.
The data ideally requires curating. However, the amount of data
that is continuously flowing in a social area network, in most
cases data curation is an impossible task.

The unsupervised learning has shown a great success in many

modern AI applications, such as face detection, object
detection, and so on.

Reinforcement Learning:
Definition :
Reinforcement Learning (RL) is a type of machine learning
where an agent learns to make decisions by interacting with an
environment. The agent receives rewards or penalties based
on its actions and aims to maximize the total reward over time.
 How Reinforcement Learning Works
1. Agent – The learner (e.g., a robot, AI in a game).
2. Environment – The world in which the agent operates (e.g., a
chessboard, a self-driving car’s surroundings).
3. Actions (A) – The choices the agent can make.
4. State (S) – The current situation of the agent in the
environment.
5. Reward (R) – Feedback given to the agent (positive for good
actions, negative for bad actions).
6. Policy (π) – The strategy that the agent follows to choose
actions.

The agent explores different actions, learns from rewards, and

optimizes its policy to make the best possible decisions.

Example: Teaching a Robot to Walk

Imagine we have a robot that needs to learn how to walk:
 State (S): Robot’s current position and balance.
 Actions (A): Move left leg, move right leg, shift weight, etc.
 Reward (R): +10 for staying balanced, -10 for falling.
 Goal: Maximize total rewards to learn walking efficiently.
At first, the robot will randomly try different movements. Over
time, it learns which actions help it stay balanced and moves
forward more efficiently.

Ex: Consider training a pet dog, we train our pet to bring a ball
to us. We throw the ball at a certain distance and ask the dog to
fetch it back to us. Every time the dog does this right, we
reward the dog. Slowly, the dog learns that doing the job rightly
gives him a reward and then the dog starts doing the job right
way every time in future. Exactly, this concept is applied in
“Reinforcement” type of learning. The technique was initially
 developed for machines to play games. The machine is given an
algorithm to analyze all possible moves at each stage of the
game. The machine may select one of the moves at random. If
the move is right, the machine is rewarded, otherwise it may be
penalized. Slowly, the machine will start differentiating between
right and wrong moves and after several iterations would learn
to solve the game puzzle with a better accuracy. The accuracy of
winning the game would improve as the machine plays more
and more games.

Deep Learning
Definition: Deep Learning is a type of machine learning that
uses artificial neural networks (ANNs) to process data and make
decisions. It is inspired by the human brain and can learn from
large amounts of data without being explicitly programmed.

How Deep Learning Works?

Deep learning models use multiple layers of artificial neurons
to learn patterns in data. These layers are called deep neural
networks (DNNs).
Structure of a Neural Network:
1. Input Layer – Takes raw data (e.g., images, text, or numbers).
2. Hidden Layers – Process and learn patterns using mathematical
functions (more layers = better learning).
3. Output Layer – Produces the final result (e.g., classification,
prediction).
Each neuron in the network applies a mathematical function
and passes information to the next layer. The model improves
over time using backpropagation and gradient descent to
adjust the neuron connections.

Example: Image Recognition (Cat vs. Dog Classifier)

 Let’s say we want a deep learning model to recognize whether
an image is of a cat or a dog.
Input: Images of cats and dogs.
Hidden Layers:
 First layer detects edges.
 Second layer detects shapes.
 Third layer detects features like eyes, ears, fur patterns.
 Output Layer: Predicts if the image is a cat or a dog.
Over time, as the model sees more images, it improves its
accuracy by adjusting its weights through training.

Key Components in Deep Learning

✔ Neurons – Basic units that process information.
✔ Weights & Biases – Adjustments made during learning.
✔ Activation Functions – Help decide whether a neuron should
be active (e.g., ReLU, Sigmoid).
✔ Loss Function – Measures how good or bad the model is
performing.
✔ Backpropagation – A technique to fine-tune weights for
better accuracy.

Deep Reinforcement Learning :

The Deep Reinforcement Learning (DRL) combines the
techniques of both deep and reinforcement learning. The
reinforcement learning algorithms like Q-learning are now
combined with deep learning to create a powerful DRL model.
The technique has been with a great success in the fields of
robotics, video games, finance and healthcare. Many previously
unsolvable problems are now solved by creating DRL models.
There is lots of research going on in this area and this is very
actively pursued by the industries.
So far, you have got a brief introduction to various machine
learning models, now let us explore slightly deeper into various
algorithms that are available under these models.