A I AI
What is A rtificial I ntelligence ( AI ) :
AI is a branch of computer science devoted to the study of computer designed to imitate the thinking and reasoning power of the human mind.
To build a programs that can perform intelligent tasks we need :
1-Knowledge representation schemes ( how to represent knowledge inside the
machine computer)
2-How to reach conclusions for the represented knowledge (inference)
3-Search methods.
Over View of some
AI
Applications :
Two most, fundamental concerns of A.I. researches are knowledge representation and search, the first of these addresses the problem of capturing in a formal language.
Search is a problem solving techniques that systematically explores a space states might include the different board configuration in a game or intermediate steps in a reasoning process. This space of alternative solutions is then searched to find a final answer.
Example : search for the best :
A
2
5
E
B
7
10
10
C
8
F
3
D
The paths from A to D as the following:
1) A
B
C
D = 5+7+8 =20
2) A
D = 10 (( the best path))
3) A
E
F
D = 2+10 +3= 15
1
1- Game Playing:
Much of early research in state space search was done using common board game such as chess and the 8-puzzle . Most games are played using a well defined set of rules, this makes it easy to generate the search space and frees the researcher from many of ambiguities and complexities.
2- Automated Reasoning and Theorem Proving:
Automatic theorem proving is the oldest branch of artificial intelligence. Theorem proving research was responsible for much of the early work in formalizing search algorithms and developing formal representation languages such as predicate calculus and logic programming ( PROLOG ).
3- Expert Systems :
Expert knowledge is a combination of a theoretical understanding of the problem and collection heuristic problem solving rules.
Expert systems are constructed by obtaining this knowledge from a human expert and coding it into a form that a computer may apply to similar problems.
I
4- Natural Language Understanding and Semantic Modeling :
One of the long-standing goals of artificial intelligence is the creations of programs that are capable of understanding human language. Understanding natural language involves much more than parsing sentences into their individual parts of speech and looking those words up in a dictionary. Real understanding depends on extensive background knowledge about the domain of discourse and the idioms used in that domain.
2
5- Parallel Distributed Processing (PDP) :
Most of the techniques presented in this text use explicitly represented knowledge and carefully designed search algorithms to implement intelligence. A very different approach seeks to build intelligent programs using models that parallel the structure of neurons in the human brain.
Neural architectures also provide a natural model for parallelism, because each neuron is an independent unit.
6-Artificial Neural Networks :
Artificial neural networks as physical cellular networks that are able to acquire, store, and utilize experiential knowledge has been related to the network's capabilities and performance.
Figure (0) : The McCulloch-Pitts model of Neural Network
1-Knowledge Representation :
The process of acquisition of knowledge could be carry out manually or automatically. In manual mode, knowledge receives from one or more domain experts.
Whereas in automatic mode, a machine learning system is used for autonomous learning and refining knowledge from the external world.
Now knowledge after acquisition can be represented by various tools and techniques such:
3
1 Logic Representation
1-1 Propositional Calculus.
1-2 Predicate Calculus .
2 Production Rules Systems.
3 Networks Representation
3-1 Semantic Nets Representation.
3-2 Conceptual Graph.
3-3 Frames and Scripts Representation.
3-4 Petri Nets Representation
4
