zbMATH — the first resource for mathematics

Training feedforward neural networks using genetic algorithms. (English) Zbl 0709.68060
IJCAI 89, Proc. Int. Conf., Detroit, MI/USA 1989, 762-767 (1989).
[For the entire collection see Zbl 0707.68001.]
Neural networks and genetic algorithms are two techniques for optimization and learning. Sections 2 and 3 give an overview of neural networks and genetic algorithms, respectively, with a special emphasis on their strengths and weaknesses. Section 4 describes the data on which the experiments were run: processing of passive sonar data from arrays of underwater acoustic receivers (representing the input from a BBN’s expert system into the field). In Section 5 the generic algorithm used for training feedforward networks is discussed. Section 6 is devoted to the series of experiments leading to the final version of the generic algorithm, also compared (and outperformed) to the backpropagation method.
Reviewer: N.Curteanu

68T05 Learning and adaptive systems in artificial intelligence
68T35 Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence
92B20 Neural networks for/in biological studies, artificial life and related topics
68Q85 Models and methods for concurrent and distributed computing (process algebras, bisimulation, transition nets, etc.)