artificial intelligence

By s.bhavani T.BHAVANITHYA c.calab joseph ECE-A

Artificial Intelligence: definitions

Artificial Intelligence is behavior by a machine that.If performed by a human being would be called intelligent(Well-publicized) Artificial Intelligence is the study of how to make computers do things at which , at the moment .people are better AI basically a theory of how the human mind word (Mark Fox)

What is AI?

How does the human brain work?

How do we emulate the human brain?
How do we create intelligence?

What is intelligence?

Who cares? Lets do some cool and useful stuff!

How do we classify research as AI?

Does it investigate the brain?

Does it investigate intelligence?
Does it emulate the brain?

Is it intelligent?

If we dont know how it works, then its AI. When we find out how it works, its not AI anymore

What is Intelligence?

The ability to learn and to cope. The ability to contemplate, think, and reason.

What are the objectives of Artificial Intelligence?

What AI is not.

AI is not the study and creation of conventional computers systems. Even though one can argue

that all programs exhibit some degree of intelligence an AI program will go beyond this in demonstrating a high level of intelligence required of human in performing some task.

AI is not the study of mind nor of the body nor of languages as customarily found in the fields of psychology ,physiology, cognitive science or linguistics.

But in AI the goal is to develop working computer systems that are truly capable of performing tasks that require high levels of intelligence. The imp point is that the systems all be capable of performing intelligent tasks effectively and efficiently.

History of AI
1943: "Colossus", the first electronic computer was created 1950: The Turing Test was proposed by Alan Turing 1951: Marvin Minksy and Dean Edmonds built first neural network where the computer simulated a rat finding its way through a maze. 1958: John McCarthy and Marvin Minsky founded AI lab at MIT 1958: LISP developed by a team led by John McCarthy. LISP was the first non-procedural programming language which is still used for

HISTORY
1966: Joseph Weizenbaum wrote a program called "Eliza". The program was like a therapist and asked questions of patients. 1969: Stanford University built a robot called "Shakey" which could recognize shapes and colours and navigate a path through coloured blocks 1970s: The first expert systems appeared

shakey

HISTORY
1997: Super computer "Deep Blue" defeated world champion chess player Gary Kasparov 1997: First time AI system controlled a space craft "Deep Space II" late 1990s: web bots and crawlers developed to give information to search engines for internet Present programmers are still trying to develop a computer which can successfully pass The Turing Test

LISP Programming Language

Overview: LISP (LISt Processor) is generally regarded as the language for AI. LISP was formulated by AI pioneer John McCarthy in the late 50's. Although LISP doesn't have a built-in inference mechanism, inference processes can be implemented into LISP very easily. LISP's essential data structure is an ordered sequence of elements called a "list."

LISP
Originally, LISP was built around a small set of simple list-manipulating functions which were building blocks for defining other, more complex functions. Today's LISPs have many functions and features which facilitate development efforts. Among contemporary implementations and dialects, have gained acceptance as a standard.

LISP..
The elements may be irreducible entities called "atoms" (functions, names or numbers) or they can be other lists. Lists are essential for AI work because of their flexibility: a programmer need not specify in advance the number or type of elements in a list. Also, lists can be used to represent an almost limitless array of things, from expert rules to computer programs to thought processes to system components.

Limitations...
To date, all the traits of human intelligence have not been captured and applied together to spawn an intelligent artificial creature. Currently, Artificial Intelligence rather seems to focus on lucrative domain specific applications, which do not necessarily require the full extent of AI capabilities. This limit of machine intelligence is known to researchers as narrow intelligence.

Technology...
There are many different approaches to Artificial Intelligence, none of which are either completely right or wrong. Some are obviously more suited than others in some cases, but any working alternative can be defended. Over the years, trends have emerged based on the state of mind of influencial researchers, funding opportunities as well as available computer hardware. Over the past five decades, AI research has mostly been focusing on solving specific problems. Numerous solutions have been devised and improved to do so efficiently and reliably. This explains why the field of Artificial Intelligence is split into many branches, ranging from Pattern Recognition to Artificial Life, including Evolutionary Computation and Planning.

APPROACHES AND TOOLS

APPROACHES
Artificial Intelligence (AI) is a subfield of computer science closely tied with biology and cognitive science
AI is concerned with computing techniques and models that simulate/investigate intelligent behavior AI research builds upon our understanding of the brain and evolutionary development in return, AI research provides insights into the way the brain works, as well as the larger process of biological evolution

Cybernetics and brain simulation

Cybernetics is about having a goal and taking action to achieve that goal. Knowing whether you have reached your goal (or at least are getting closer to it) requires "feedback", a concept that comes from cybernetics.

Cybernetics and brain simulation

In the 1940s and 1950s, a number of researchers explored the connection between neurology, information theory, and cybernetics. Some of them built machines that used electronic networks to exhibit rudimentary intelligence, such as W. Grey Walters turtles and the Johns Hopkins Beast. Many of these researchers gathered for meetings of the Teleological Society at Princeton University and the Ratio Club in England. By 1960, this approach was largely abandoned, although elements of it would be revived in the 1980s.

Symbolic
When access to digital computers became possible in the middle 1950s, AI research began to explore the possibility that human intelligence could be reduced to symbol manipulation

Cognitive simulation
Cognitive science is the interdisciplinary study of mind and intelligence, e.g., how information is represented and transformed in a brain or in a machine. It consists of multiple research disciplines, including psychology, artificial intelligence, philosophy, neuroscience, learning sciences, linguistics, anthropology, sociology, and education. It spans many levels of analysis, from low-level learning and decision mechanisms to high-level logic and planning; from neural circuitry to modular brain organization.

Applied Cognitive Science

Computational models of human reasoning

Problem solving Scientific thinking

Models of non-introspective mental processes

Language comprehension, language learning Human memory organization (STM, LTM)

Knowledge based
When computers with large memories became available around 1970, researchers from all three traditions began to build knowledge into AI applications. This "knowledge revolution" led to the development and deployment of expert systems(introduced by Edward Feigenbaum), the first truly successful form of AI software. The knowledge revolution was also driven by the realization that enormous amounts of knowledge would be required by many simple AI applications.

Sub-symbolic
During the 1960s, symbolic approaches had achieved great success at simulating high-level thinking in small demonstration programs. Approaches based on cybernetics or neural networks were abandoned or pushed into the background. By the 1980s, however, progress in symbolic AI seemed to stall and many believed that symbolic systems would never be able to imitate all the processes of human cognition, especially perception, robotics, learning and pattern recognition. A number of researchers began to look into "sub-symbolic" approaches to specific AI problems

Statistical
In the 1990s, AI researchers developed sophisticated mathematical tools to solve specific subproblems. These tools are truly scientific, in the sense that their results are both measurable and verifiable, and they have been responsible for many of AI's recent successes.

TOOLS
In the course of 50 years of research, AI has developed a large number of tools to solve the most difficult problems in computer science. A few of the most general of these methods are : Search and optimization Logic Probabilistic methods for uncertain reasoning Classifiers and statistical learning methods

Neural networks
Control theory Languages

Search and optimization

In computer science, a search algorithm, broadly speaking, is an algorithm for finding an item with specified properties among a collection of items. The items may be stored individually as records in a database; or may be elements of a search space defined by a mathematical formula or procedure, such as the roots of an equation with integer variables; or a combination of the two, such as the Hamiltonian circuits of a graph.

GA-OVERVIEW
Developed: USA in the 1970s Early names: J. Holland, K. DeJong, D. Goldberg Typically applied to:
discrete optimization

Attributed features:
not too fast good heuristic for combinatorial problems

Special Features:
Traditionally emphasizes combining information from good parents (crossover) many variants, e.g., reproduction models, operators

 Hollands original GA is now known as the simple genetic algorithm (SGA) Other GAs use different:
Representations Mutations Crossovers Selection mechanisms

Biological Background (1) The cell

Every animal cell is a complex of many small factories working together The center of this all is the cell nucleus The nucleus contains the genetic information

The Evolutionary Cycle

selection
parents

modification
modified offspring

initiate & evaluate

population

evaluation
evaluated offspring deleted members

discard

Components of a GA
A problem to solve, and ... Encoding technique (gene, chromosome) Initialization procedure (creation) Evaluation function (environment) Selection of parents (reproduction) Genetic operators (mutation, recombination) Parameter settings (practice and art)

ALGORITHM

Benefits of Genetic Algorithms

Concept is easy to understand Modular, separate from application Supports multi-objective optimization Good for noisy environments Always an answer; answer gets better with time Inherently parallel; easily distributed

 Many ways to speed up and improve a GAbased application as knowledge about problem domain is gained Easy to exploit previous or alternate solutions Flexible building blocks for hybrid applications Substantial history and range of use

When to Use a GA
Alternate solutions are too slow or overly complicated Need an exploratory tool to examine new approaches Problem is similar to one that has already been successfully solved by using a GA Want to hybridize with an existing solution Benefits of the GA technology meet key problem requirements

Some GA Application Types

Domain
Control Design Scheduling Robotics Machine Learning Signal Processing Game Playing Combinatorial Optimization

Application Types
gas pipeline, pole balancing, missile evasion, pursuit semiconductor layout, aircraft design, keyboard configuration, communication networks manufacturing, facility scheduling, resource allocation trajectory planning designing neural networks, improving classification algorithms, classifier systems filter design poker, checkers, prisoners dilemma set covering, travelling salesman, routing, bin packing, graph colouring and partitioning

What Are Artificial Neural Networks?

An extremely simplified model of the brain Essentially a function approximator Transforms inputs into outputs to the best of its ability

 Composed of many neurons that cooperate to perform the desired function

 Traditionally, the term neural network had been used to refer to a network or circuit of biological neurons. The modern usage of the term often refers to artificial neural networks, which are composed of artificial neurons or nodes. Thus the term has two distinct usages

Artificial neural networks are made up of interconnecting artificial neurons (programming constructs that mimic the properties of biological neurons). Artificial neural networks may either be used to gain an understanding of biological neural networks, or for solving artificial intelligence problems without necessarily creating a model of a real biological system. The real, biological nervous system is highly complex and includes some features that may seem superfluous based on an understanding of artificial networks.

 A neural network (NN), in the case of artificial neurons called artificial neural network (ANN) or simulated neural network (SNN), is an interconnected group of natural or artificialneurons that uses a mathematical or computational model for information processing based on a connectionistic approach to computation. In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network. In more practical terms neural networks are non-linear statistical data modeling or decision making tools. They can be used to model complex relationships between inputs and outputs or to find patterns in data.

Applications of natural and of artificial neural networks

The utility of artificial neural network models lies in the fact that they can be used to infer a function from observations and also to use it. This is particularly useful in applications where the complexity of the data or task makes the design of such a function by hand impractical.

Application areas of ANNs include system identification and control (vehicle control, process control), game-playing and decision making (backgammon, chess, racing), pattern recognition (radar systems, face identification, object recognition, etc.), sequence recognition (gesture, speech, handwritten text recognition), medical diagnosis, financial applications, data mining (or knowledge discovery in databases, "KDD"), visualization and e-mail spam filtering.

Evaluating progress
In 1950, Alan Turing proposed a general procedure to test the intelligence of an agent now known as the Turing test. This procedure allows almost all the major problems of artificial intelligence to be tested. However, it is a very difficult challenge and at present all agents fail. Artificial intelligence can also be evaluated on specific problems such as small problems in chemistry, hand-writing recognition and game-playing. Such tests have been termed subject matter expert Turing tests. Smaller problems provide more achievable goals and there are an ever-increasing number of positive results.

 The broad classes of outcome for an AI test are: Optimal: it is not possible to perform better Strong super-human: performs better than all humans Super-human: performs better than most humans Sub-human: performs worse than most humans For example, performance at draughts is optimal , performance at chess is super-human and nearing strong super-human, and performance at many everyday tasks performed by humans is sub-human.

APPLICATIONS

 Successfully used in a wide range of fields including medical diagnosis ,stock trading, robot control, law, scientific discovery, video games, toys, and Web search engines. There are many competitions held to promote AI The main areas are: general machine intelligence, conversational behavior, data-mining, driverless cars, robot soccer and games.

 A lot of cutting edge AI has filtered into general applications, often without being called AI because once something becomes useful enough and common enough it's not labeled AI anymore U call it as AI EFFECT

Computer science
Time sharing Interactive interpreters Graphical user interfaces and the computer mouse Rapid development environments The linked list data type Automatic storage management Symbolic programming Functional programming Dynamic programming Object-oriented programming

finance
Banks use AI to organize operations, invest in stocks, and manage properties. Financial institutions have long used artificial neural network systems to detect charges or claims outside of the norm, flagging these for human investigation.

In August 2001, robots beat humans in a simulated financial trading competition.

medicine
A medical clinic can use artificial intelligence systems to organize bed schedules, make a staff rotation, and provide medical information. Artificial neural networks are used for medical diagnosis functioning as machine differential diagnosis.

Heavy industries
Robots have become common in many industries. They are often given jobs that are considered dangerous to humans. Robots have proven effective in jobs that are very repetitive which may lead to mistakes or accidents due to a lapse in concentration and other jobs which humans may find degrading

TRANSPORTATION
Fuzzy logic controllers have been developed for automatic gearboxes in automobiles (the 2006 Audi TT, VW Toureg and VW Caravell feature the DSP transmission which utilizes Fuzzy logic, a number of koda variants (koda Fabia) also currently include a Fuzzy Logic based controller).

SKODA FABIA- A CAR WITH AUTOMATIC GEARBOXES

TELECOMMUNICATION
Telecommunication companies use heuristic search in scheduling applications BT groups uses this to provide work schedules for 20000 engineers

Toys and games

music
With AI, scientists are trying to make the computer emulate the activities of the skillful musician. Composition, performance, music theory, sound processing are some of the major areas on which research in Music and Artificial Intelligence are focusing. Contribution is less

aviation
The AOD has use for artificial intelligence for surrogate operators for combat and training simulators, mission management aids, support systems for tactical decision making, and post processing of the simulator data into symbolic summaries Multiple aircraft are needed to get good approximations for some calculations so computer simulated pilots are used to gather data. These computer simulated pilots are also used to train future air traffic controllers. The AOD also uses artificial intelligence in speech recognition software.

 In 2003, NASAs Dryden Flight Research Center, and many other companies, created software that could enable a damaged aircraft to continue flight until a safe landing zone can be reached. The Intelligent Flight Control System was tested on an F-15

robotics
REMOTE CONTROL: Remote control in high-tech warfare has begun to extend to robots involved in surveillance, troop supply and even the firing of powerful weapons A monkey feeds itself by operating a prosthetic arm with its mind. Best robot-2007

A new device trades on that thinking and aims to partially restore the experience of vision for the blind and visually impaired by relying on the nerves on the tongue's surface to send light signals to the brain

cleverbots
Chatterbots are computer programs designed to have conversations with humans. The best chatterbots use some form of artificial intelligence to learn how to generate better dialogue over time. Rollo Carpenter has developed a chatterbot Cleverbot is Carpenters latest chatting AI and uses a growing database of 20+ million online conversations to talk with anyone who goes to its website. At this stage in its development, talking to Cleverbot is like having a text conversation with a monkey tied to a typewriter as it is being flung down a flight of stairs. www.cleverbot.com

eurega
Eureqa examines data from an experiment, and produces equations that explain what happened. Sounds like a scientist to me.

Other fields
Robotics
Behavior-based robotics Cognitive Cybernetics Developmental robotics Epigenetic robotics Evolutionary robotics

Hybrid intelligent system Intelligent agent Intelligent control Litigation

Automated reasoning Automation Biologically inspired computing Concept mining Data mining Knowledge representation Semantic Web E-mail spam filtering

 Pattern recognition
Optical character recognition Handwriting recognition Speech recognition Face recognition

Artificial Creativity Computer vision, Virtual reality and Image processing Diagnosis (artificial intelligence) Game theory and Strategic planning Game artificial intelligence and Computer game bot Natural language processing, Translation and Chatterbots Nonlinear control and Robotics