Analytical estimates of efficiency of attractor neural networks with inborn connections
The analysis is restricted to the features of neural networks endowed to the latter by the inborn (not learned) connections. We study attractor neural networks in which for almost all operation time the activity resides in close vicinity of a relatively small number of attractor states. The number o...
Main Authors: | Solovyeva Ksenia, Karandashev Iakov, Dunin-Barkowski Witali |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2016-01-01
|
Series: | ITM Web of Conferences |
Online Access: | http://dx.doi.org/10.1051/itmconf/20160602009 |
Similar Items
-
MODELS OF INNATE NEURAL ATTRACTORS AND THEIR APPLICATIONS FOR NEURALINFORMATION PROCESSING
by: Ksenia P. Solovyeva, et al.
Published: (2016-01-01) -
Editorial: Toward and Beyond Human-Level AI
by: Witali Dunin-Barkowski
Published: (2020-12-01) -
Attractors of autoencoders : Memorization in neural networks
by: Strandqvist, Jonas
Published: (2020) -
The use of different temperatures in attractor neural networks
by: Almeida, Jorge Filipe de Albuquerque Matos de
Published: (1996) -
Analytical attractor for Bjorken flows
by: Jean-Paul Blaizot, et al.
Published: (2021-09-01)