MACHINE LEARNING

PCS 206

1
Overview

Machine Learning
Supervised Learning
Unsupervised Learning

2
 Goal of Artificial Intelligence

 Development of computers/machine that can be taught rather than

programmed

 Simulation of intelligence
• Machine should be adaptable to new situations
• Capable of learning from experience

3
Machine Learning: Introduction
• Subfield of artificial intelligence (AI)
• Provides systems the ability to automatically learn and improve from experience
without being explicitly programmed. 
• Machine learning focuses on the development of computer programs that can
access data and use it learn for themselves.

4
 Learning
is an important
aspect of
intelligence

5
 Machine Learning begins with DATA
• The process of learning begins with observations or data
• Examples: direct experience, or instruction, in order to look for patterns in data
and make better decisions in the future based on the examples that we provide. 
• The primary aim is to allow the computers learn automatically without
human intervention or assistance and adjust actions accordingly.

6
 Machine Learning Algorithms
• Machine Learning methods are broadly classified into following
categories:

Supervised Learning Unsupervised learning

Algorithm generates a function that

No labelled examples are available
maps input to desired function

Labelled data Eg. Clustering, association rule mining

Eg. Classification and regression

7
 Supervised Learning: Training
• Data mining task of inferring a function from labeled training data.
• The training data consist of a set of training examples.
• In supervised learning, each example is a pair consisting of an input object
(typically a vector) and the desired output value.

8
 Supervised Learning…Contd.
• A supervised learning algorithm analyzes the training data
• Produces an inferred function
• This function is used for mapping new examples.

9
 Supervised Learning…Testing
• An optimal scenario will allow for the algorithm to correctly determine the class
labels for unseen instances.
• This requires the learning algorithm to generalize from the training data to unseen
situations in a “reasonable” way.
• Eg. classification and regression algorithms

10
Supervised Classification

11
12
 Unsupervised Learning
• The information used to train is neither classified nor labeled.
• U.L studies how systems can infer a function to describe a hidden structure from
unlabeled data.
• The system doesn’t figure out the right output, but it explores the data and can
differentiate the given input data.
• All clustering algorithms fall under supervised learning.

13