Paper
8 June 2005 Mechanism of memory in connected neural networks
Toshihiro Shimizu
Author Affiliations +
Proceedings Volume 5851, Fundamental Problems of Optoelectronics and Microelectronics II; (2005) https://doi.org/10.1117/12.634384
Event: Fundamental Problems of Optoelectronics and Microelectronics II, 2004, Khabrovsk, Russian Federation
Abstract
In a global neural network, which consists of many connected local neural networks the mechanism of memory and the information flow are discussed. One of local neural networks in the global network is connected with an input network, which provides some pattern (or some information) to the global network from outside. We assume the nearest-neighbor coupling between local networks in the global netowrk. The local netowrk can exchange the pattern or information among nearest-neighbor local networks in the global network. The local netowrk can exchange the pattern or information among nearest-neighbor local netowrks and the patterns can propagate in the global system. The propagation of the pattern persists even after the connection between the input network and one of local networks in the global network was decoupled. For the appropriate nearest-neighbor coupling the propagated pattern generates a global pattern and it does not disappear. We study the role of the local coupling in the genesis of a global pattern and in memorization of the information inputted from the outside.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Toshihiro Shimizu "Mechanism of memory in connected neural networks", Proc. SPIE 5851, Fundamental Problems of Optoelectronics and Microelectronics II, (8 June 2005); https://doi.org/10.1117/12.634384
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neurons

Neural networks

Data processing

Process modeling

Systems modeling

Brain

Content addressable memory

RELATED CONTENT

Fast learning method for RAAM based on sensitivity analysis
Proceedings of SPIE (November 25 2014)
Implementation aspects of Graph Neural Networks
Proceedings of SPIE (October 25 2013)
Neural network approach to numeric array sorting
Proceedings of SPIE (November 06 2019)
Relaxation matching by the Hopfield neural network
Proceedings of SPIE (March 04 1996)
Basic concept of dynamic behavior
Proceedings of SPIE (March 30 2000)

Back to Top