Artificial Intelligence: Introduction, History, and Applications - CS 401 Lecture Notes, Lecture notes of Artificial Intelligence

Download Artificial Intelligence: Introduction, History, and Applications - CS 401 Lecture Notes and more Lecture notes Artificial Intelligence in PDF only on Docsity!

CS 401

Artificial Intelligence

Lecture # 01 Monday, January 28, 2019 Spring 2019 FAST – NUCES, Faisalabad Campus Zain Iqbal [email protected]

Brief Intro

• Course that focuses on the study and design of IntelligentAgents

Today’sTopics

 Introduction toAI  History  Applications  Agents  About this course ◦ Organization ◦ Goals/objectives

Intelligence and Machines – A

perspective

 What is Intelligence?  Is it possible for a “machine” to be intelligent?  Can machines think?  Can machines decide?  Can we emulate intelligent behavior in machines?  How far can we take it?

What is Intelligence?

 More scientific definition Intelligence is a measure of the success of an entity in achieving its objectives by interacting with its environment. Reveals important points…  Presence of an environment to observe intelligent behavior  Measure goals on a scale to measure intelligence

What is Intelligence?

It provides us possibility of intelligent machines  The ability to express intelligence depends on the richness of interaction with the environment, and on the achievement of the goals as well as internal mechanisms

What is Intelligence?

 So an intelligent entity interacts with its surroundings and it implies followings: ◦ Some form of getting input ◦ A way to produce output ◦ Ability to process input to give the output some relevance

Artificial intelligence is the simulation of intelligence in machines

Think like Human

“Cognitive approach” Three ways to do this:

• Through introspection
  • Through psychological experiments
• Through brain imaging

Act like Human

“Turing test approach” Six disciplines are required:

• Natural language processing,
  • Knowledge representation,
    • Automated reasoning,
      • Machine learning,
        • Computer vision,
          • Robotics

Act Rationally

“Rational agent approach” Merits:

• More general than “laws of thought” approach
• More adjustable to scientific development This course is about designing rational/intelligent agents

HISTORY

Abridged history of AI

 1943  1950  1956  1950s  1952 - 69  1966 - 73  1969 - 79  1980 --  1987 --  1995 --  2001 -- McCulloch & Pitts: Boolean circuit model of brain Turing's "Computing Machinery and Intelligence" Birth of AI – Dartmouth:"Artificial Intelligence“ adopted Early AI programs, including Samuel's checkers program, Newell & Simon's LogicTheorist, Look,Ma,no hands! AI discovers computational complexity No progress seemed in Machine Evolution Neural network research almost disappears Early development of knowledge-based systems AI becomes an industry AI becomes a science Emergence of intelligent agents Availability of very large data sets

According to Douglas Hofstadter these are:

- To respond to situations flexibly If the same response is exhibited each time, the behavior is called mechanical. To survive in changing environments, one need to exhibit innovative behavior. - To make sense out of ambiguous or contradictory messages We understand such messages because our knowledge and experience allows us to place them in context. (e.g. time flies like an arrow) Another Perspective of Intelligence