29 October 1993 Storing temporal sequences of patterns in neural networks
Author Affiliations +
Abstract
This paper presents neural network models for storing terminating and cyclic temporal sequences of patterns under synchronous, sequential and asynchronous dynamics. We use fully interconnected neural networks with asymmetric weight connections for synchronous and sequential dynamics and a layered neural network with feedback for asynchronous dynamics. The network were successfully implemented and the number of patterns that could be stored and recalled was approximately 12% of the size of the patterns in the network.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dilip Krishnaswamy, Dilip Krishnaswamy, Kishan Mehrotra, Kishan Mehrotra, Chilukuri K. Mohan, Chilukuri K. Mohan, Sanjay Ranka, Sanjay Ranka, } "Storing temporal sequences of patterns in neural networks", Proc. SPIE 2032, Neural and Stochastic Methods in Image and Signal Processing II, (29 October 1993); doi: 10.1117/12.162028; https://doi.org/10.1117/12.162028
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT


Back to Top