Fundamentals of the new artificial intelligence. Beyond traditional paradigms (Q4384488)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1145202
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Fundamentals of the new artificial intelligence. Beyond traditional paradigms |
scientific article; zbMATH DE number 1145202 |
Statements
26 April 1998
0 references
neural networks
0 references
genetic algorithms
0 references
fuzzy systems
0 references
rough sets
0 references
chaotic systems
0 references
backpropagation procedure
0 references
dynamical system theory
0 references
Fundamentals of the new artificial intelligence. Beyond traditional paradigms (English)
0 references
The book presents a basic knowledge and algorithms about some recent fields of artificial intelligence, namely neural networks, genetic algorithms, fuzzy systems, rough sets, and chaotic systems. The presentation is easy to learn, to be useful in practice. To the basic techniques of neural networks belongs the backpropagation procedure, which enables one an interactive improving the weight coefficients of the corresponding neural network. Another types of neural networks, namely Hopfield-Tank model for optimization problems, and Kohonen model for competitive learning are also described. Genetic algorithms represent, in general, guided random search methods. A typical genetic algorithm contains the following steps: initialization of the population, reproduction, crossover breeding, random mutation. It is shown by example, how the technique can solve the traveling salesman problem. Fuzzy systems provide techniques for solving hard problems in designing, controlling and realizing various systems. They are suitable not only to store, retrieve or process fuzzy information, but also to infer it as a conclusion from uncertain or approximate premises in fuzzy logical expert systems. The rough set theory gives a new technique for reasoning from imprecise and ambiguous data. A short overview of both rough set theory and knowledge representation systems is presented, and some tasks solvable by corresponding procedures are outlined. Chaos is one of the hardest nonlinear problems; there is no standard definition of it. A hopeful way is to define chaos as a dynamical system whose steady state solution is a chaotic attractor. Therefore, the last chapter mainly deals with dynamical system theory, state and phase spaces, cobwebs and attractors.
0 references