artificial intelligence (ai) the science and engineering of creating computer systems that simulate...

I Robot

A.I.

D.A.R.Y.L

Artificial Intelligence (AI)

The science and engineering of creating computer systems that

simulate human thought and behavior.

Alan Turing:English mathematician

Known for his belief that computers would

someday be as intelligent as humans.

Turing TestTest to determine if a computer exhibited human intelligence.

Can you tell who the robot is by conversation?If not, then the robot is intelligent. ??

Many uses for Artificial Intelligence Software

Assists us with evaluating and interpreting large amounts of data.

Can act as an informed advisor with difficult decisions

Can provide a challenging game opponent in a virtual reality computer-generated world or in a

game of chess.

Requirements:A set of logical rules to apply to the input to produce

useful output

Instructions for how to handle unexpected input(the ability for the software to “wing it”)

The ability to learn with experience to become better at what it is designed to do (machine learning)

Artificial Intelligence

Conventional A.I.

Computational Intelligence

Conventional Artificial Intelligence

Expert systems

Case-based reasoning

Bayesian networks

Behavior-based AI

Conventional Artificial Intelligence

Expert systems

Software that functions like a human expert in a particular field or area.

Some are used to diagnose disease

Some are used to diagnose mechanical engine failure

Some are used to predict future weather events

Some are used to design new products

Conventional Artificial Intelligence

Case-based reasoning

The AI software maintains a library of problem cases and solutions

Relies on the four R’s for solving new problems

Retrieve: Find cases in the case library relevant to the new problem.

Reuse:

Revise:

Retain:

Map the solutions from a previous case or cases to the variables of the new problem, adjusting where necessary.

Test the solution and revise if necessary

Store the new problem and its newly acquired successful solution as a case in the library.

Conventional Artificial Intelligence

Bayesian networks

A graphical model that represents a set of variables and their relationships and

dependencies

For Example:

A Bayesian network could be designed to represent the variables in a person’s behavior, physical chemistry, and family history to determine the likeliness that the person suffers from depression

Conventional Artificial Intelligence

Behavior-based AI

Simulates intelligence by combining many semi-autonomous modules.

Each module has a specific activity for which it is responsible

By combining these simple modules, the resulting system exhibits intelligent

behavior; it becomes smarter than the sum of its parts.

Computational Intelligence(develops intelligence through an iterative process)

Neural Networks

Simulates the functioning of the neutron in a human brain

It “learns” by the affects of the neural pathways

Some specific features of neural networks:

• The ability to retrieve information even if some of the neural nodes fail.

• Fast modification of stored data as a result of new information

• The ability to discover relationships and trends in large databases

• The ability to solve complex problems for which all of the information is not present

Computational Intelligence

Fuzzy Systems

Deals with reasoning that is approximate rather than precise.

Computational Intelligence

Evolutionary Computation

Includes areas of AI that derive intelligence by attempting many solutions and throwing away the

ones that don’t work.

“A survival of the fittest” approach

Genetic Algorithm:

Used to solve large, complex problems where a number of algorithms or models change and evolve until the best one emerges. VIDEO

A.I. Applications•Robotics

Involves developing mechanical or computer devices to perform tasks that require a high degree of precision or are tedious or hazardous for humans.

•Computer VisionCombines hardware and AI software that permit computers to capture, store, and interpret visual images and pictures. (Can be used to give robots vision)

video

A.I. Applications•Natural Language Processing

Uses AI techniques to enable computers to generate and understand natural human languages, such as English. Ex. Speech Recognition

•Handwriting RecognitionUses AI techniques to enable computers to translate handwritten characters or words into computer-readable data.

A.I. Applications•Face Recognition

A form of computer vision that uses cameras and AI software to identify individuals by unique facial characteristics.

•Intelligent AgentsConsists of programs and a knowledge base used to perform a specific task for a person, a process, or another program.

A.I. Applications•Artificial Creativity

A branch of AI that works to program computers to express themselves through art, music, poetry, and other expressive outlets.

video

Virtual Reality•A computer simulated environment that can be

manipulated by a user.

Immersive virtual realityA simulation in which the user becomes fully immersed in an artificial, three-dimensional

world that is completely generated by a computer

Clip 1 Clip 2 Clip 3 Clip 4