Concept Learning - University of Minnesota Duluth

Concept Learning

? Learning from examples ? General-to-specific ordering over hypotheses ? Version Spaces and candidate elimination

algorithm ? Picking new examples ? The need for inductive bias

CS 5751 Machine

Chapter 2 Concept Learning

1

Learning

Some Examples for SmileyFaces

Eyes Nose Head Fcolor Hair? Smile?

CS 5751 Machine

Chapter 2 Concept Learning

2

Learning

Features from Computer View

Eyes Nose Head Fcolor Round Triangle Round Purple Square Square Square Green Square Triangle Round Yellow Round Triangle Round Green Square Square Round Yellow

Hair? Yes Yes Yes No Yes

Smile? Yes No Yes No Yes

CS 5751 Machine

Chapter 2 Concept Learning

3

Learning

Representing Hypotheses

Many possible representations for hypotheses h

Idea: h as conjunctions of constraints on features

Each constraint can be:

? a specific value (e.g., Nose = Square)

? don't care (e.g., Eyes = ?)

? no value allowed (e.g., Water=?)

For example,

Eyes Nose Head Fcolor Hair?

?

CS 5751 Machine

Chapter 2 Concept Learning

4

Learning

Prototypical Concept Learning Task

Given:

? Instances X: Faces, each described by the attributes Eyes, Nose, Head, Fcolor, and Hair?

? Target function c: Smile? : X -> { no, yes }

? Hypotheses H: Conjunctions of literals such as

? Training examples D: Positive and negative examples of the target function < x1, c(x1) >, < x2 , c(x2 ) >,..., < xm , c(xm ) >

Determine: a hypothesis h in H such that h(x)=c(x) for all x in D.

CS 5751 Machine

Chapter 2 Concept Learning

5

Learning

 ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download