Lecture 1 – AI Background

Dr. Muhammad Adnan Hashmi

1

Profile: Name: Dr. Muhammad Adnan Hashmi 2005: BSc (Hons.) in CS – University of the

Punjab, Lahore, Pakistan 2007: MS in Multi-Agent Systems– University

Paris 5, Paris, France 2012: PhD in Artificial Intelligence – University

Paris 6, Paris, France. Coordinates:

Email: adnan.hashmi@ciitlahore.edu.pk

2

Primary Book: Artificial Intelligence: A Modern Approach (AIMA) Authors: Stuart Russell and Peter Norvig (3rd Ed.) Advisable that each student should purchase a

copy of this book

Reference Book:1. Artificial Intelligence (Fourth Edition) by George F

Luger

3

1. Provide a concrete grasp of the fundamentals of various techniques and branches that currently constitute the field of Artificial Intelligence, e.g.,

1. Search2. Knowledge Representation3. Autonomous planning4. Machine learning5. Robotics etc.

4

Course overview

What is AI?

A brief history of AI

The state of the art of AI

Introduction and Agents (Chapters 1,2)

Search (Chapters 3,4,5,6)

Logic (Chapters 7,8,9)

Planning (Chapters 11,12)

Learning (Chapters 18,20)

Views of AI fall into four categories: Systems that act like humans Systems that think like humans Systems that act rationally Systems that think rationally

In this course, we are going to focus on systems that act rationally, i.e., the creation, design and implementation of rational agents.

Turing (1950) "Computing machinery and intelligence": "Can machines think?" "Can machines behave intelligently?"

Operational test for intelligent behavior: the Imitation Game

Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes

Anticipated all major arguments against AI in following 50 years

Suggested major components of AI: knowledge, reasoning, language understanding, learning.

1960s “Cognitive Revolution": Information-processing psychology replaced prevailing orthodoxy of behaviorism

Requires scientific theories of internal activities of the brain. How to validate? Cognitive Science: Predicting and testing

behavior of human subjects Cognitive Neuroscience: Direct identification from

neurological data Both approaches are now distinct from AI, and

share with AI the following characteristic: The available theories do not explain (or

engender) anything resembling human-level general intelligence.

Normative rather than descriptive Aristotle: What are correct thought processes? Several Greek schools developed various forms of logic:

Notation and rules of derivation for thoughts (this may or may not have proceeded to the idea of mechanization)

Direct line through mathematics and philosophy to modern AI

Problems: Not all intelligent behavior is mediated by logical

deliberation What is the purpose of thinking? What thoughts

should I have out of all the thoughts (logical or otherwise) that I could have?

Rational behavior: doing the right thing The right thing: the optimal (best) thing that is

expected to maximize the chances of achieving a set of goals, in a given situation

Doesn't necessarily involve thinking, but a rational agent should be able to demonstrate it artificially, in moving towards its goal

Aristotle (Nicomachean Ethics): Every art and every inquiry, and similarly

every action and pursuit, is thought to aim at some good.

An agent is an entity that perceives and acts This course is about designing rational/intelligent

agents Abstractly, an agent is a function from percept

histories to actions: f : P* -> A

For any given class of environments and tasks, we seek the agent (or class of agents) with the optimal (best) performance

Caveat: computational limitations make perfect rationality unachievable So we attempt to design the best (most

intelligent) program, under the given resources.

Philosophy: Logic, methods of reasoning, mind as physical system, foundations of learning, language, rationality

Mathematics: Formal representation and proof, Algorithms, Computation, (un)decidability, (in)tractability, probability

Psychology: Adaptation, phenomena of perception and motor control, experimental techniques (with animals, etc.)

Economics: Formal theory of rational decisions Linguistics: Knowledge representation, grammar Neuroscience: Plastic physical substrate for mental

activity Control theory: Homeostatic systems, Stability, Simple

optimal agent designs.

1943 McCulloch & Pitts: Boolean circuit model of brain 1950 Turing's "Computing Machinery and Intelligence" 1956 Dartmouth: "Artificial Intelligence“ adopted 1952-69 Look, Ma, no hands! 1950s Early AI programs, including Samuel's checkers

program, Newell & Simon's Logic Theorist, 1965 Robinson's algo for logical reasoning 1966-73 AI discovers computational complexity

Neural network research almost disappears 1969-79 Early development of knowledge-based systems 1980-- AI becomes an industry 1986-- Neural networks return to popularity 1987--AI becomes a science 1995--The emergence of intelligent agents.

Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997

No hands across America (driving autonomously 98% of the time from Pittsburgh to San Diego)

During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people

NASA's on-board autonomous planning program controlled the scheduling of operations for a spacecraft

Proverb solves crossword puzzles better than most humans.

Speech technologies Automatic speech recognition (ASR) Text-to-speech synthesis (TTS) Dialog systems

Language Processing Technologies Machine Translation Information Extraction Informtation Retrieval Text classification, Spam filtering.

17

18

Computer Vision: Object and Character Recognition Image Classification Scenario Reconstruction etc.

Game-Playing Strategy/FPS games, Deep Blue etc.

Logic-based programs Proving theorems Reasoning etc.

19

20