You are on page 1of 74

The branch of computer science which aims to create machines with intelligence or making intelligence machines.

Basis of field is that intelligence can be portrayed by a machine. Which raises many philosophical questions.

Artificial Intelligence (AI)

computational part of the ability to achieve goals in the world

Computers making decisions in real-world problems

apply

formulate

solve

Genetic Algorithms: An evolutionary algorithm which generates each individual from some encoded form known as a "chromosome" or "genome". Chromosomes are combined or mutated to breed new individuals.
Evolutionary Computing: An algorithm which incorporates aspects of natural selection or survival of the fittest. An evolutionary algorithm maintains a population of structures (usually randomly generated initially), that evolves according to rules of selection, recombination, mutation and survival, referred to as genetic operators.

Artificial Intelligence: the branch of computer science that deal with writing computer programs that can solve problems creatively; "workers in AI hope to imitate or duplicate intelligence in computers and robots"

Alan Turing(1912-1954)
Father of computer science Turing test for AI

Marvin Minsky (MIT)


Built first Neural network computer SNARC

John McCarthy ( Stanford University )


Developed LISP, AI programming language

Computational Computational process? Computational Computational

models of human behavior? models of human thought systems that behave intelligently? systems that behave rationally !

Mundane Tasks:
Perception
Vision Speech

Natural Languages
Understanding Generation Translation

Formal Tasks

Common sense reasoning Robot Control Games : chess, checkers etc Mathematics: Geometry, logic,Proving properties of programs Engineering ( Design, Fault finding, Manufacturing planning) Scientific Analysis Medical Diagnosis Financial Analysis

Expert Tasks:

Intelligence requires Knowledge Knowledge posesses less desirable properties such as:
Voluminous Hard to characterize accurately Constantly changing Differs from data that can be used

AI technique is a method that exploits knowledge that should be represented in such a way that:
Knowledge captures generalization It can be understood by people who must provide it It can be easily modified to correct errors. It can be used in variety of situations

10

Computer beats human in a chess game. Computer-human conversation using speech


recognition.

Expert system controls a spacecraft. Robot can walk on stairs and hold a cup of water. Language translation for webpages.

Home appliances use fuzzy logic. ......


11

Artificial intelligence (AI)


Computers with the ability to mimic or duplicate the functions of the human brain

Artificial intelligence systems


The people, procedures, hardware, software, data, and knowledge needed to develop computer systems and machines that demonstrate the characteristics of intelligence

Intelligent behaviour

Learn from experience Apply knowledge acquired from experience Handle complex situations Solve problems when important information is missing Determine what is important React quickly and correctly to a new situation Understand visual images Process and manipulate symbols Be creative and imaginative Use heuristics

Perceiving the world around it,


a rational agent selects an action to maximize the performance measure

Using
Evidence provided in perception sensors Built in knowledge of the agent

Perceptive system
A system that approximates the way a human sees, hears, and feels objects

Vision system
Capture, store, and manipulate visual images and pictures

Robotics Expert system


Mechanical and computer devices that perform tedious tasks with high precision Stores knowledge and makes inferences

Learning system
Computer changes how it functions or reacts to situations based on feedback

Natural language processing


Computers understand and react to statements and commands made in a natural language, such as English

Neural network
Computer system that can act like or simulate the functioning of the human brain

Schematic

Artificial intelligence

Vision systems Robotics

Learning systems Expert systems

Neural networks Natural language processing

The branch of computer science concerned with making computers behave like humans. The term was coined in 1956 by John McCarthy at the Massachusetts Institute of Technology. Artificial intelligence includes
games playing: programming computers to play games such as chess and checkers expert systems : programming computers to make decisions in real-life situations (for example, some expert systems help doctors diagnose diseases based on symptoms) natural language : programming computers to understand natural human languages

neural networks : Systems that simulate intelligence by attempting to reproduce the types of physical connections that occur in animal brains robotics : programming computers to see and hear and react to other sensory stimuli

Currently, no computers exhibit full artificial intelligence (that is, are able to simulate human behavior). The greatest advances have occurred in the field of games playing. The best computer chess programs are now capable of beating humans. In May, 1997, an IBM super-computer called Deep Blue defeated world chess champion

Gary Kasparov in a chess match.


In the area of robotics, computers are now widely used in assembly plants, but they are capable only of very limited tasks. Robots have great difficulty identifying objects based on appearance or feel, and they still move and handle objects clumsily. Natural-language processing offers the greatest potential rewards because it would allow people to interact with computers without needing any specialized knowledge. You could simply walk up to a

computer and talk to it. Unfortunately, programming computers to understand natural languages has proved to be more difficult than originally thought. Some rudimentary translation systems that translate from one human language to another are in existence, but they are not nearly as good as human translators. There are also voice recognition systems that can convert spoken sounds into written words, but they do not understand what they are writing; they simply take dictation. Even these systems are quite limited -you must speak slowly and distinctly.

In the early 1980s, expert systems were believed to represent the future of artificial intelligence and of computers in general. To date, however, they have not lived up to expectations. Many expert systems help human experts in such fields as medicine and engineering, but they are very expensive to produce and are helpful only in special situations.
Today, the hottest area of artificial intelligence is neural networks, which are proving successful in a number of disciplines such as voice recognition and natural-language processing.

There are several programming languages that are known as AI languages because they are used almost exclusively for AI applications. The two most common are LISP and Prolog.

A computer can be considered to be smart only when a human interviewer, conversing with both an unseen human being and an unseen computer, can not determine which is which

Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson 6th ed, Copyright 2001, Prentice Hall, Upper Saddle River, NJ

24

Medical Diagnosis Robot Control Law Stock Trading Toys

When a discovered technique of human intelligence reaches mainstream (in the form of toys or medical equipment) it is no longer considered artificial intelligence but enter artificial life (a field of study which examines systems related to life).

Isaac Asimov wrote a set of three rules in his classic I, Robot which all robots must obey:

A robot may not injure a human being or, through inaction, allow a human being to come to harm. A robot must obey orders given to it by human beings, except where such orders would conflict with the First Law. A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.

Creating a singular program/entity capable of independent, creative thought. Creating a species of programs/entities. (i.e. web-bots) Is Deep Blue intelligent?

Artificial Life: The study of synthetic systems which behave like natural living systems in some way. Artificial Life complements the traditional biological sciences concerned with the analysis of living organisms by attempting to create lifelike behaviors within computers and other artificial media.

AI technology could have some undesired consequences for the human race:
Decreased demand for human labor Enhancement of human ability or experience Redefinition of human identity and basic values (e.g. intelligence)

Servants: Star Wars (R2D2) Comrade: Star Trek Lt. Commander Data Extension of Human Abilities: Ghost in the Shell Conqueror: The Matrix A Race: Starcraft

General issues and applications of AI , Problem solving, Search strategies, Intelligent searching , Knowledge Representation, First order predicate logic, , Frames Conceptual dependency Game playing Problem solving using Planning,

Several futurists argue that artificial intelligence will transcend the limits of progress and human intelligence. This idea is based on Moores Law:
Relentless exponential improvement in digital technology with uncanny accuracy. This law predicts that desktop computers will have the same processing power as human brains by the year 2029.

This law predicts that desktop computers will have the same processing power as human brains by the year 2029. 2045: AI will reach a point where it is able to improve itself at a rate that far exceeds anything in the past.

Several futurists believe that human beings and robots will merge to create cyborgs (e.g. Star Trek Data) more capable and powerful than either. This idea is called transhumanism. Ghost in the Shell is an example of transhumanism in fiction.

CSAIL Robotics Engineer One of the worlds leading designers of robot swarms-group of robots that work together for a greater purpose.

James McLurkin

MIT

MIT Media Lab A young engineer who designs robots to communicate and interact the way people do.

Cynthia Breazeal

MIT

Uncertainty handling, Fuzzy Logic based inferencing, Machine learning introduction to neural networks and genetic algorithms, Expert Systems, Natural Language Processing

Efloys group/community behavior made of simpler behaviors Traveling SalesPerson mind-numbing tasks using genetic algorithms Conway's Game of Life simple cellular behavior Self Replicating Loops complex cellular behavior Neural Networks Adaptive behavior

The Evolution of selfreplicating loops

Colonies???

New ways to solve problems? New problems to solve? Pattern recognition security applications. Redundancy the internet. Study/breakdown of real world behaviors.

If we create artificial intelligence/life, is it murder to pull the plug? Will we allow a community to develop its own rules/morals? Will we see each other as a threat? (Skynet) What can we learn about ourselves watching artificial beings interact?

Video games, Robocup, NERO Theorem proving Speech recognition Understanding natural language (stories) Machine translation (English-Russian) Robotics (Computer vision)

The spirit is willing but the flesh is weak The vodka is strong but the meat is rotten

Driving autonomous vehicles Tactical guidance system for military aircraft Satellite meta command system Automatic operation of trains Robots for micro-surgery

Security applications:

Inspection of manufactured parts. Bin picking. Visual Inspection of objects (e.g. fruits). Medical Intelligent Tutoring Systems. Transportation. Medical Applications:
Diagnosis NMR/X-Ray Slides Diagnosis Determination of mineral resources.

Fingerprint applications Facial identification.

Navigation system for automatic cars Cruise control for automobiles Single button control of washing machines Camera autofocus Back light control for camcorders Auto motor control of vacuum cleaners Camera aiming for sporting events

Artificial Intelligence/Life are providing new methods of solving problems. The study of one or more life forms is providing insight into organic behaviors. Organic behavior is helping to solve age-old and some new problems. Will we ever produce a truly intelligent machine?

Let S be the set of states (strings) Input: Initial state: s0 Neighbor generator, N: S 2S Goal function, G: S {0,1}

s1,,sn such that:


s1,,sn S for all 1in, si N(si-1) G(sn) = 1

Were very impressed. Meaning? Rush Hour 8-puzzle Logistics 8-queens problem Logic puzzles Job-shop scheduling

Move cars forward and backward to escape

States: configurations of cars N(s): reachable states G(s): 1 if red car at gate

Slide tiles into order States:

N(s):
G(s):

1 6
4

2
5 8

3 7
6 1

7 4

8 3

Very sophisticated. What goes where when?

Desert Storm logistics paid for AI research

No captures States: N(s): G(s):

1.

2.

Jody, who is an ape, wasnt the ape who returned immediately after Tom and immediately before the animal who appeared in the movie with no rating. The only lions that were used in the movies were the one who was the third to return, the one who appeared in the R movie, and the one who appeared in Luck.

Industrial problem: Allocate machines and machinists to time slots Constraints on orders in which parts are serviced

s0

s0

What makes one search scheme better than another?


Completeness: Find solution? Time complexity: How long? Space complexity: Memory? Optimality: Find shortest path?

Let |T(s)| b (branching factor), goal at depth d How implement priority queue? Completeness? Time complexity? Space complexity? Optimality?

Completeness? Time complexity? Space complexity? Optimality?


yes O(bd)

Yes

O(bd)

Completeness?

Time complexity?

Yes, assuming state space finite


O(|S |), can do well if lots of goals

Space complexity? Optimality?


No

O(n), n deepest point of search

DFS, only expand nodes depth l. Completeness?

Time complexity?

No, if l d. O(bl) O(l)

Space complexity?
Optimality?
No

Depth limited, increasing l. Completeness?

Time complexity?
O(d) Yes

Yes.

Space complexity?
Optimality?

O(bd), even with repeated work!

BFS in both directions Need N-1 How could this help?


bl vs 2bl/2

What makes this hard to implement?

More permanent Ease of duplication and dissemination Less expensive Consistent and thorough Can be documented Can execute certain tasks much faster than a human can Can perform certain tasks better than many or even most people

Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson 6th ed, Copyright 2001, Prentice Hall, Upper Saddle River, NJ

70

Natural intelligence is creative People use sensory experience directly Can use a wide context of experience in different situations AI - Very Narrow Focus

71

RoboCup is an international research effort to promote autonomous robots.

Robots must cooperate in


Strategy acquisition Real-time reasoning Multi-agent collaboration Competition against another team of robots

Each robot has


Pentium 233MHz Linux OS Video camera and frame grabber Sensor System Kicker