ARTIFICIAL INTELLIGENCE Chapter 1

ARTIFICIAL INTELLIGENCE Chapter # 1

• Table of Contents • • 1. What is Artificial Intelligence? 2. The AI problems 3. The underlying assumptions 4. What is an AI Technique

What is AI? • AI is the study of how to make computers do things which, at the moment, people do better. Or Its simply the mapping of human brain to the machine.

AI Problems • Early work in the field is focused on formal tasks. • Game playing • Theorem proving • Eg: checkers playing programs(samuel). • Early this was assumed that computers could perform well at those tasks simply by being fast at exploring large number of solution paths and then selecting the best one.

Continue. . • Next AI focused on the sort of problem solving that we do every day when we decide how to get to work in the morning, often called commonsense reasoning. • To investigate such sort of reasoning , newell, shaw and simon built the general problem solver, which they applied to severl commonsense tasks. • Ai research progressed and techniques of handling larger amount of world knowledge were developed, this include perception, NLU and problem solving.

Some of the Task Domains of Artificial Intelligence

Some of the Task Domains of Artificial Intelligence

Some of the Task Domains of Artificial Intelligence

• The problem areas where AI is now flourishing most as practical discipline are primarily the domain that require specialized expertise without the assistance of common sense knowledge

Tic Tac Toe 1 • Board Move table A vector of 19, 683 elements

Tic Tac Toe 2 Board

Way 3

Example

Continue. .

Algorithm 4

Question Answering Example • Mary went shopping for a new coat. She found a red one she really liked. When she got it home, she discovered that it went perfectly with her favorite dress. • Q 1 : What did Mary go shopping for? • Q 1 : What did Mary find that she liked? • Q 1 : Did Mary buy anything?

Way/ Algorithm 1

Continue. .

• Example: What did Mary go shopping for? • Text pattern: Mary go shopping for Z. • Possible substitutions: • Mary goes shopping for z OR Mary went shopping for z • Z is a new coat after matching text pattern to input text. • Answer for 2 nd question according to this method is “red one” which is exactly not correct • It is not able to answer the third question.

Second way/ algorithm • This program first convert the input text into structural internal form that attempts to capture the meaning of the sentence. • It also convert questions into that form. • It finds answers by matching structure forms against each other. • Three ways are used for structural internal forms: i) production rules ii) slotfiller structure iii) mathematical logic. • Example: she found a red one that she really liked.

A Structure Representation of a Sentence

Way 3/ Algorithm • It combines the previous structure form with other structure forms that describes prior knowledge about the objects and situations involved in the text. • This is known as augmented knowledge structure. • We are going to made a “worldmodel” which represents background world knowledge.

A Shopping Script