In this session
Artificial Intelligence
Introduction to LLMs
Unit 6.1 : Introduction
Understanding AI
Unit 2.1 Revisiting AI, ML, DL
Machine Learning
Unit 2.1 Revisiting AI, ML, DL
Machine Learning : Examples
Unit 2.1 Revisiting AI, ML, DL
Machine Learning : Examples
Unit 2.1 Revisiting AI, ML, DL
Deep Learning
Unit 2.1 Revisiting AI, ML, DL
Deep Learning : Examples
Unit 2.1 Revisiting AI, ML, DL
Common Terminologies
Unit 2.1 Revisiting AI, ML, DL
Common Terminologies
Unit 2.1 Revisiting AI, ML, DL
Common Terminologies
Unit 2.1 Revisiting AI, ML, DL
Common Terminologies
Unit 2.1 Revisiting AI, ML, DL
Common Terminologies
Unit 2.2 Modelling
In general, there are two approaches taken by researchers when building AI models.
They either take a rule-based approach or learning approach.
Unit 2.2 Modelling
Types of AI Models
Unit 2.2 Modelling
Rule Based Approach
A Rule based approach is generally based on the data
and rules fed to the machine, where the machine reacts
accordingly to deliver the desired output.
Unit 2.2 Modelling
Rule Based Approach : Scenario
A clothing website has a Chabot to answer questions about order tracking.
Data: The Chabot doesn't require a massive dataset for training. It relies on a
predefined set of questions and corresponding answers.
Rules: The Chabot uses a decision tree approach with clearly defined rules to
understand user queries and provide responses. Here's a simplified example:
Rule 1: If message includes “track order,” “shipment status,” → go to order tracking
Rule 2 (within tracking):
Ask for order number if not provided
Validate order number and show tracking info
If invalid → show error + prompt again
Rule 3: If message doesn’t match any rule → suggest FAQ or support
Unit 2.2 Modelling
Rule Based Approach : Scenario
A clothing website has a Chabot to answer questions about order tracking.
Drawbacks:
• Static Learning: Rule-based systems don’t adapt; once trained, they
operate strictly on predefined data and logic.
• Lack of Adaptability: They fail when exposed to unfamiliar inputs and
cannot learn from new data or user feedback.
• No Self-Improvement: Unlike machine learning models, rule-based
systems can't evolve over time or adjust to changing patterns or rules.
Unit 2.2 Modelling
Learning Based Approach
Under learning approach, the machine is fed
with data and the desired output to which the
machine designs its own algorithm (or set of
rules) to match the data to the desired output
fed into the machine
Unit 2.2 Modelling
Learning Based Approach : Scenario
Under learning approach, the machine is fed with data and
the desired output to which the machine designs its own
algorithm (or set of rules) to match the data to the desired
output fed into the machine
Unit 2.2 Modelling
Learning Based Approach
Unit 2.2 Modelling
Supervised Learning
In a supervised learning model, the dataset which is fed
to the machine is labelled. A label is some information
which can be used as a tag for data.
For example, students get grades according to the
marks they secure in examinations. These grades are
labels which categorize the students according to their
marks.
Unit 2.2 Modelling
Supervised Learning : Example
Unit 2.2 Modelling
Unsupervised Learning
An unsupervised learning model works on unlabelled dataset.
This means that the data which is fed to the machine is random
and there is a possibility that the person who is training the
model does not have any information regarding it.
The unsupervised learning models are used to identify
relationships, patterns and trends out of the data which is fed
into it.
Unit 2.2 Modelling
Unsupervised Learning
Unit 2.2 Modelling
Unit 2.2 Modelling
Unit 2.2 Modelling
Unit 2.2 Modelling
Supervised vs Unsupervised Learning
Unit 2.2 Modelling
Reinforcement Learning
This learning approach enables the computer to make a series of decisions that maximize a
reward metric for the task without human intervention and without being explicitly
programmed to achieve the task.
Unit 2.2 Modelling
Reinforcement Learning
Unit 2.2 Modelling
Summary
Unit 2.2 Modelling
Sub-Categories
Unit 2.2 Modelling
Sub-Categories of Supervised Learning Models
Unit 2.2 Modelling
Sub-Categories of Supervised Learning Models
Unit 2.2 Modelling
Sub-Categories of Supervised Learning Models
Unit 2.2 Modelling
Sub-Categories of Supervised Learning Models
Unit 2.2 Modelling
Sub-Categories of Unsupervised Learning Models
Unit 2.2 Modelling
Sub-Categories of Unsupervised Learning Models
Unit 2.2 Modelling
Sub-Categories of Unsupervised Learning Models
Unit 2.2 Modelling
Sub-Categories of Unsupervised Learning Models
Unit 2.2 Modelling
Sub categories of Unsupervised Learning Models
Unit 2.2 Modelling
Unit 2.2 Modelling
Unit 2.2 Modelling
Sub-Categories of Deep Learning Models
Unit 2.2 Modelling
Sub-Categories of Deep Learning Models
Unit 2.3 Artificial Neural Networks
Unit 2.2 Modelling
How does AI make a decision?
Introduction to LLMs
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
Revision Time:
