Scribd
Upload
5 views1 page

Machine Learning Fundamentals and Design

The document outlines the distinction between Artificial Intelligence (AI) and Machine Learning (ML), highlighting that ML is a subset of AI focused on learning from data. It discusses the interdisciplinary nature of ML, the definition of learning, and provides an example of a learning task. Additionally, it details the steps involved in designing a learning system and addresses various issues and methods in machine learning.

Uploaded by

Praneetha Siripurapu
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
5 views1 page

Machine Learning Fundamentals and Design

The document outlines the distinction between Artificial Intelligence (AI) and Machine Learning (ML), highlighting that ML is a subset of AI focused on learning from data. It discusses the interdisciplinary nature of ML, the definition of learning, and provides an example of a learning task. Additionally, it details the steps involved in designing a learning system and addresses various issues and methods in machine learning.

Uploaded by

Praneetha Siripurapu
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

■ Machine Learning - Well Posed Learning

Problem & Designing a Learning System

■ **Artificial Intelligence vs Machine Learning**


Artificial Intelligence (AI) is the broad field where machines mimic human intelligence such
as reasoning, problem-solving, and decision-making. Machine Learning (ML) is a subset of
AI that focuses specifically on *learning from experience* (data) to improve performance
on tasks.

■ **Disciplines relevant to ML**


ML takes ideas and methods from several fields like statistics, AI, Bayesian methods,
psychology, control theory, and more. This makes it a highly interdisciplinary subject.

■ **Definition of Learning**
A program learns if: its performance at a task (T), measured by performance metric (P),
improves with experience (E).

■ **Example: Learning to play checkers**


Task (T) Play Checkers
Performance (P) Percentage of games won
Experience (E) Self-play against itself

■ **Designing a Learning System involves 5 steps:**


1. Choosing the training experience 2. Choosing the target function 3. Choosing a
representation for the target function 4. Choosing a function approximation algorithm 5.
Final design integration

■ **Issues in Machine Learning**


• How many examples are needed? • How noisy data affects learning? • How hypothesis
complexity impacts generalization? • What are the theoretical limits of learnability?

■ **Learning Methods**
1. Neural Networks → Direct experience 2. Reinforcement Learning → Indirect experience
3. Evolutionary Algorithms → Indirect experience

You might also like