The Computational Capabilities of Neural Networks

0404164 - UIVT-O 20010033 RIV AT eng C - Konferenční příspěvek (zahraniční konf.)
Šíma, Jiří
The Computational Capabilities of Neural Networks.
Artificial Neural Nets and Genetic Algorithms. Proceedings of the International conference. Wien: Springer, 2001 - (Kůrková, V.; Steele, N.; Neruda, R.; Kárný, M.), s. 22-26. ISBN 3-211-83651-9.
[ICANNGA'2001 /5./. Praha (CZ), 22.04.2001-25.04.2001]
Grant CEP: GA MŠMT LN00A056
Klíčová slova: computational power * computational complexity * perceptrons * radial basis functions * spiking neurons * probabilistic computation * analog computation
Kód oboru RIV: BA - Obecná matematika
https://link.springer.com/book/10.1007/978-3-7091-6230-9#toc

We survey and summarize the existing literature on the computational aspects of neural network models, by presenting a detailed taxonomy of the various models according to their computational characteristics. The criteria of classification include e.g. the architecture of the network, time model, state type, weight constraints, network size, computation type, etc. The underlying results concerning the computational power of perceptron, RBF, winner-take-all, and spiking neural networks are briefly surveyed.
Trvalý link: http://hdl.handle.net/11104/0124431