Translator Disclaimer
Paper
7 December 1994 Closed multilayer dynamic neural network for pattern time sequence processing
Author Affiliations +
Proceedings Volume 2430, Optical Memory & Neural Networks '94: Optical Neural Networks; (1994) https://doi.org/10.1117/12.195592
Event: Optical Memory and Neural Networks: International Conference, 1994, Moscow, Russian Federation
Abstract
A closed multilayer dynamic neural network, unlike a nonclosed one, can form infinite pattern sequences, both periodic and aperiodic. The closing enhances interactions between time pattern sequences and formation of new sequences. Methods of recording time sequences are considered; prospects of use are discussed.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Vladimir B. Kotov and Nickolay Yu Kulakov "Closed multilayer dynamic neural network for pattern time sequence processing", Proc. SPIE 2430, Optical Memory & Neural Networks '94: Optical Neural Networks, (7 December 1994); https://doi.org/10.1117/12.195592
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Two new classes of Boltzmann machines
Proceedings of SPIE (August 19 1993)
Feature space trajectory (FST) classifier neural network
Proceedings of SPIE (October 10 1994)
Boltzmann machines for image-block coding
Proceedings of SPIE (March 28 1995)
Fuzzy Hopfield-Tank TSP model
Proceedings of SPIE (March 22 1999)
License plate recognition system
Proceedings of SPIE (October 01 1998)

Back to Top