Artificial Intelligence

Sabrina Jackson

Artificial Intelligence, or AI for short is the area of computer science that is focusing on creating machines to do things that would require intelligence if done by human. AI is a combination of computer science, physiology, and philosophy. AI is a broad topic, consisting of different fields, from machine vision to expert systems. The element that the fields of AI have in common is the creation of machines that can "think". Researchers are creating systems which can mimic human thought, understanding , speech, beat the best human chess player, and countless other feasts never before possible.

Strong AI:

Claim that computers can be made to actually think, just like human beings do. More precisely, the claim that there exist a class computer program really thinking?

Weak AI:

Claim that computers are important tools in the modeling and simulation of human activity.

 

Serial computers is distinguished by its capabilities to handle only one operation at a time in a series/sequences of steps within a given domain.

 

AI programs and analyzes pose what can be called the PROBLEMS OF WHAT TO DO NEXT. Exploring your alternatives to see which moves to make next is the issue of Search. Search is divided into two major types Blind search and Heuristic search.

 

BLIND SEARCH

The space of alternatives must be structured into a graph or a tree. Semantics nets are one type of graph, and hierarchies are often trees.

 

When searching with a TREE a given node can only be reached by one PATH. A tree in AI program is a collection of NODES and ARCS are arranged in the structure of a tree in nature. The TREE has a ROOT NODE from which BRANCHES divide into more branches. This BRANCHING FACTOR is the number of alternatives.

HEURISTIC SEARCH

Definitions

Semantic memory is typified by general, impersonal facts

1. A semantic network or simply NET is a set of NODES and connecting LINKS that represent prepositional information.

 

2. Rule-Based Representation

The if-then or situation-action, the knowledge that if a certain situation exists then a certain action should be taken.

Chess is a domain in which a if-then situation occurs, i.e. if I move here then what will my opponents strategy be to counter that move favorably. These are rule- based representations.

Other sites of interest

ThinkQuest AI competition site (comprehensive site on AI)

Glossary of AI Terms

Introduction to Artificial Intelligence

Introduction to Artificial Intelligence (Syracuse)

Introduction to Neural Networks (Syracuse)

Neural Networks Basic Ideas

What is a Neural Network?

Artifical Neurons


Back to CS Outline