Scribd
Upload
135 views

Unit-3-Second Chapter

This document provides an overview of rule learning concepts including: 1) Propositional and first-order logic, with examples of how first-order logic can represent more complex statements. 2) Converting decision trees into rules using an iterative inductive algorithm. 3) Heuristic rule induction using separate-and-conquer and information gain approaches. 4) First-order Horn-clause induction using Inductive Logic Programming (ILP) techniques like the FOIL algorithm. 5) Learning recursive rules using inverse resolution, GOLEM/CIGOL, and PROGOL algorithms.

Uploaded by

vamsi kiran
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
135 views

Unit-3-Second Chapter

This document provides an overview of rule learning concepts including: 1) Propositional and first-order logic, with examples of how first-order logic can represent more complex statements. 2) Converting decision trees into rules using an iterative inductive algorithm. 3) Heuristic rule induction using separate-and-conquer and information gain approaches. 4) First-order Horn-clause induction using Inductive Logic Programming (ILP) techniques like the FOIL algorithm. 5) Learning recursive rules using inverse resolution, GOLEM/CIGOL, and PROGOL algorithms.

Uploaded by

vamsi kiran
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
You are on page 1/ 9

UNIT III

Chapter-2 Rule Learning:

1) Propositional and First-Order,


2) Translating decision trees into rules,
3) Heuristic rule induction using separate and conquer and information gain,
4) First-order Horn-clause induction (Inductive Logic Programming) and Foil,
5) Learning recursive rules,
 Inverse resolution,
 Golem
 Progol.

Introduction on Rule Learning/ Learning Rules

1
1) Propositional and First-Order
What is propositional logic?
Propositional logic (PL) is declarative, so it guides us on how to represent information in a
logical form and draw conclusions.
We can only represent information as either true or false in propositional logic.
Disadvantages of PL
 If you want to represent complicated sentences or natural language statements, PL is not
sufficient.
 There is very limited expressive power in PL, so we use FOL instead.
The sentence shown below cannot be represented we cannot using PL logic.
Examples
1. I love mankind. It’s the people I can’t stand!
2. Joe Root likes football.
3. I like to eat mangos.
PL is not enough to represent the sentences above, so we require powerful logic (such as FOL).
What is first-order logic (FOL)?
1. FOL is a mode of representation in Artificial Intelligence. It is an extension of PL.
2. FOL represents natural language statements in a concise way.
3. FOL is also called predicate logic. It is a powerful language used to develop information about an
object and express the relationship between objects.
4. FOL not only assumes that does the world contains facts (like PL does), but it also assumes the
following:
o Objects: A, B, people, numbers, colors, wars, theories, squares, pit, etc.
o Relations: It is unary relation such as red, round, sister of, brother of, etc.
o Function: father of, best friend, third inning of, end of, etc.
Parts of first-order logic
FOL also has two parts:
1. Syntax
2. Semantics
Syntax
The syntax of FOL decides which collection of symbols is a logical expression.
The basic syntactic elements of FOL are symbols. We use symbols to write statements in
shorthand notation.

2
Basic elements of FOL

Name Symbol
Constant 1, 6, A,W,New York, Elie, Dog...
Variables a, b, c, x, y, z...
Predicates <, >, brother, sister, father...
Equality ==
Function Sqrt, LessThan, Sin(θ)...
Quantifier ∀, ∃
Connectives ∧, ∨, ¬, ⇒, ⇔

2)Translating decision trees into rules

 Inductive Learning Algorithm (ILA) is an iterative and inductive machine learning


algorithm which is used for generating a set of a classification rule, which produces rules of the
form “IF-THEN

3
4
3) Heuristic rule induction using separate and conquer and information gain

5
4) First-order Horn-clause induction (Inductive Logic Programming) and Foil

6
7
5) Learning recursive rules
 Inverse resolution

8
 Golem /Cigol

 Progol

You might also like