๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Retrieval of pattern sequences at variable speeds in a neural network with delays

โœ Scribed by Tom M. Heskes; Stan Gielen

Publisher
Elsevier Science
Year
1992
Tongue
English
Weight
578 KB
Volume
5
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.

โœฆ Synopsis

We discuss a neural network for the storage and retrieval of sequences of patterns. Assuming a distribution of delays, short relative to the duration of each of the single patterns, and assuming adaptive thresholds, we show that a sequence of patterns, learned at a particular speed, can be replayed at variable speeds. The retrieval speed can be adjusted by a threshold adaptation constant. The effect of noise on the transitions between successive pattern states is studied.

๐Ÿ“œ SIMILAR VOLUMES

Sequences of smoothly correlated pattern
Sequences of smoothly correlated patterns in neural networks with random transmission delays
โœ M. Bartholomeus; A. C. C. Coolen ๐Ÿ“‚ Article ๐Ÿ“… 1992 ๐Ÿ› Springer-Verlag ๐ŸŒ English โš– 909 KB

A neural network with a broad distribution of transmission delays was used to study numerically the retrieval of sequences having several types of correlations between successive patterns. In the case of sequences consisting of patterns correlated for finite time, the quality of retrieval was found

Global exponential stability of a class
Global exponential stability of a class of neural networks with variable delays
โœ W. Zheng; J. Zhang ๐Ÿ“‚ Article ๐Ÿ“… 2005 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 441 KB

In this paper, the conditions ensuring existence, uniqueness, and global exponential stability of the equilibrium point of a class of neural networks with variable delays are studied. Without assuming global Lipschitz conditions on these activation functions, applying idea of vector Lyapunov functio