L1: Introduction to Artificial Intelligence

Topics Included:
What is Intelligence? What is thought? Knowledge Pyramid What is Artificial Intelligence? What is Intelligent System? Task Domains of AI AI Techniques Level of Model Criteria for success Summary Review Questions

What is Intelligence?
The ability to reason, to trigger new thoughts , to perceive and learn is intelligence.

What is Thought?
Thiagarajan defines thought as A mechanism which a) Stimulates
i) ii) iii) iv) Action (speech and other motion functions) Further thought Information generation Knowledge generation External stimulus or Internal stimulus Present environment or Past memory Charged/discharged state of neurons Electromagnetic thought waves

b)
c) d)

Is triggered by
i) ii) i) ii) i) ii)

Acts through Is stored as

KNOWLEDGE PYRAMID
Wisdom Intelligence

Knowledge
Information Data Symbols

o Symbols form the means of representation o Data can be defined as a collection of symbols o When data are processed, one gets information

o Knowledge is organized information or knowledge can be defined as a piece of information that helps in decision making

o Intelligence can be stated as the ability to draw useful inferences from the available knowledge
o Wisdom is the maturity of mind that directs its intelligence to achieve desirable goals.

Big questions
Can machines think? And if so, how? And if not, why not? And what does this say about human beings? And what does this say about the mind?

Artificial Intelligence

The term artificial intelligence was coined by John McCarthy in 1956. Acc. to him AI is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence.

 AI is the study of how to make computers do things which, at the moment people do better. AI can also be defined as Developing computer programs to solve complex problems by applications of processes that are analogous to human reasoning processes. Association of Artificial Intelligence (AAAI) defines AI as the scientific understanding of the mechanisms, underlying thoughts and intelligent behavior and their embodiment in machines.

What is Intelligent System?

System that: does everything that I want it to do & nothing that I dont Human-like reasoning recover from failure Learns from its mistakes Adapts to its environment Makes decision about appropriateness of actions

Task domains of AI
Mundane Tasks
Perception - vision, speech Natural Language - understanding, generation, translation Commonsense reasoning Robot Control

Formal Tasks
Games - Chess, Checkers Mathematics - Geometry, logic, integral calculus

Expert Tasks
Engineering - Design, Fault finding, Manufacturing planning Scientific Analysis Medical Diagnosis

AI techniques to solve a problem

Intelligence requires Knowledge. But it has some undesirable properties:
It is voluminous It is hard to characterize accurately It is constantly changing It differs from data being organized in a way that corresponds to the ways it will be used.

Knowledge should be:

Captures generalization Understood by people who must provide it Can easily be modified Can be used even if it is not totally accurate or complete

Introductory Problem: Question Answering

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 favourite dress.

Q1: What did Mary go shopping for?

Q2: What did Mary find that she liked?

Q3: Did Mary buy anything?

Introductory Problem: Question Answering

Program 1: 1. Match predefined templates to questions to generate text patterns. 2. Match text patterns to input texts to get answers. What did X Y for? What did Mary go shopping

Mary go shopping for Z

Z = a new coat

Introductory Problem: Question Answering

Program 2: Structured representation of sentences: e.g She found a red one Event2: instance: Finding tense: Past agent: Mary object: Thing 1 she really liked. Thing1: instance: Coat colour: Red

Introductory Problem: Question Answering

Program 3:
Convert the I/p text into a structured form, combines that form with other structured forms that describe prior knowledge about the objects and situations involved in the text.

C finds M

C leaves L

C buys M
C leaves L C takes M

Level of the Model

What is our goal in trying to produce programs that do the intelligent things that people do? Are we trying to produce programs that do the tasks the same way people do? Or, are we attempting to produce programs that simply do the tasks in whatever way appears easiest? We try to make programs that attempt to model human performance.

Criteria for Success

How will we know if we have constructed a machine that is intelligent? Turing Test: In 1950, Alan Turing proposed a method for determining whether a machine can think. His method has since become known as Turing Test. Human?
Human? Machine? Machine?

Room A
Communication via telephone

Room B

Room C
Human Interrogator

Summary
Our goal in AI is to construct working programs that solve the problems we are interested in. As the amount of knowledge grows, it becomes harder to access the appropriate things when needed, so more knowledge must be added to help. When we set out to design an AI program, we should attempt to specify as well as possible the criteria for success for that particular program functioning in its restricted domain.

Review Questions
1. What are the differences between human brain and machines? 2. How would you define intelligence and Artificial Intelligence? 3. What is knowledge? What role does machine play in AI? 4. How can you say whether the machine is intelligent or not?