Scribd
Upload
2 views

Module 4_chapter 3

This document provides an introduction to learning theory within the context of AI and machine learning, outlining key concepts such as the definition of learning, types of problems, and the components of a learning model. It distinguishes between classical and adaptive machine learning systems, emphasizing the evolution from traditional to deep learning techniques. Additionally, it covers hypothesis representation, search strategies, and algorithms like Find-S, highlighting the importance of generalization and specialization in learning systems.

Uploaded by

rohith p
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Module 4_chapter 3

This document provides an introduction to learning theory within the context of AI and machine learning, outlining key concepts such as the definition of learning, types of problems, and the components of a learning model. It distinguishes between classical and adaptive machine learning systems, emphasizing the evolution from traditional to deep learning techniques. Additionally, it covers hypothesis representation, search strategies, and algorithms like Find-S, highlighting the importance of generalization and specialization in learning systems.

Uploaded by

rohith p
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

Introduction to AI &ML(21CS752)

MODULE 4
CHAPTER 3 - BASICS OF LEARNING THEORY
3.1 INTRODUCTION TO LEARNING AND ITS TYPES
Learning is a process by which one can acquire knowledge and construct new ideas or
concepts based on the experiences.
The standard definition of learning proposed by Tom Mitchell is that a program can
learn from E for the task T, and P improves with experience E.
There are two kinds of problems – well-posed and ill-posed. Computers can solve only
well-posed problems, as these have well-defined specifications and have the following
components inherent to it.
1. Class of learning tasks (T)
2. A measure of performance (P)
3. A source of experience (E)
Let x- input, χ-input space, Y –is the output space. Which is the set of all possible
outputs, that is yes/no,
Let D –dataset for n inputs.Consider, target function be: χ-> Y , that maps input to
output.
Objective: To pick a function, g: χ-> Y to appropriate hypothesis f.

Fig: Learning Environment

Learning model= Hypothesis set + Learning algorithm

Dr. Sudhamani M J, Professor, Dept. of CSE,RNSIT 1


Introduction to AI &ML(21CS752)

Classical and Adaptive ML systems.

Classic machines examine data inputs according to a predetermined set of rules, finding
patterns and relationships that can be used to generate predictions or choices. Support
vector machines, decision trees, and logistic regression are some of the most used
classical machine-learning techniques.

A class of machine learning techniques called adaptive machines, commonly referred


to as adaptive or deep learning, is created to automatically learn from data inputs
without being explicitly programmed. By learning hierarchical representations of the
input, these algorithms are able to handle more complex and unstructured data, such
as photos, videos, and natural language.

Adaptive ML is the next generation of traditional ML – the new, the improved, the better.
Even though traditional ML witnessed significant progress.

Learning Types

3.2 INTRODUCTION TO COMPUTATION LEARNING THEORY

Dr. Sudhamani M J, Professor, Dept. of CSE,RNSIT 2


Introduction to AI &ML(21CS752)

These questions are the basis of a field called ‘Computational Learning Theory’ or in
short
(COLT).

3.3 DESIGN OF A LEARNING SYSTEM

3.4 INTRODUCTION TO CONCEPT LEARNING

3.4.1 Representation of a Hypothesis

Dr. Sudhamani M J, Professor, Dept. of CSE,RNSIT 3


Introduction to AI &ML(21CS752)

3.4.2 Hypothesis Space

Hypothesis space is the set of all possible hypotheses that approximates the target
function f.

The subset of hypothesis space that is consistent with all-observed training instances is
called as Version Space.

3.4.3 Heuristic Space Search

Heuristic search is a search strategy that finds an optimized hypothesis/solution to a


problem by iteratively improving the hypothesis/solution based on a given heuristic
function or a cost measure.

3.4.4 Generalization and Specialization

Searching the Hypothesis Space

There are two ways of learning the hypothesis, consistent with all training instances
from the large hypothesis space.

1. Specialization – General to Specific learning


2. Generalization – Specific to General learning

Generalization – Specific to General Learning This learning methodology will search


through the hypothesis space for an approximate hypothesis by generalizing the most
specific hypothesis.

Specialization – General to Specific Learning This learning methodology will search


through the hypothesis space for an approximate hypothesis by specializing the most
general hypothesis.

3.4.5 Hypothesis Space Search by Find-S Algorithm

Dr. Sudhamani M J, Professor, Dept. of CSE,RNSIT 4


Introduction to AI &ML(21CS752)

Limitations of Find-S Algorithm

3.4.6 Version Spaces

List-Then-Eliminate Algorithm

Candidate Elimination Algorithm

Dr. Sudhamani M J, Professor, Dept. of CSE,RNSIT 5


Introduction to AI &ML(21CS752)

The diagrammatic representation of deriving the version space is shown below:

Deriving the Version Space

Dr. Sudhamani M J, Professor, Dept. of CSE,RNSIT 6


Introduction to AI &ML(21CS752)

Dr. Sudhamani M J, Professor, Dept. of CSE,RNSIT 7

You might also like