Oscillatory associative memory network with perfect retrieval

2004 ◽  
Vol 197 (1-2) ◽  
pp. 134-148 ◽  
Author(s):  
Takashi Nishikawa ◽  
Frank C. Hoppensteadt ◽  
Ying-Cheng Lai
Keyword(s):  
Associative Memory ◽  
Memory Network

A Reconfigurable Bidirectional Associative Memory Network with Memristor Bridge

2021 ◽  
Author(s):  
Yingying Li ◽  
Junrui Li ◽  
Jie Li ◽  
Shukai Duan ◽  
Lidan Wang ◽  
...  
Keyword(s):  
Associative Memory ◽  
Bidirectional Associative Memory ◽  
Memory Network

Associative Memory Network with Dynamic Synapses

2014 ◽  
pp. 479-483 ◽  
Author(s):  
Yuichi Katori ◽  
Yosuke Otsubo ◽  
Masato Okada ◽  
Kazuyuki Aihara
Keyword(s):  
Associative Memory ◽  
Dynamic Synapses ◽  
Memory Network

A Proposal of Multi-Module Network for Association of Patterns and Symbols

1996 ◽  
Vol 8 (4) ◽  
pp. 345-350 ◽  
Author(s):  
Yoichiro Hattori ◽  
◽  
Takeshi Furuhashi ◽  
Yoshiki Uchikawa
Keyword(s):  
Associative Memory ◽  
Construction Method ◽  
System Construction ◽  
Module Network ◽  
Brain System ◽  
Brain Functions ◽  
Construction Methods ◽  
Memory Network ◽  
Pattern Layer ◽  
The Brain

Our brain is constructed of modules, which share brain functions and work through stimulus from outside by cooperating and competing with each other. By analogizing the brain system, construction methods of artificial multi-module networks have been proposed. The authors have proposed a 2-layer associative memory network consisting of a pattern layer and a symbol layer. This paper presents a construction method for a multimodule network using the 2-layer models. We examine the association of facial patterns by the network.

Associative Memory in a Multimodular Network

1999 ◽  
Vol 11 (7) ◽  
pp. 1717-1737 ◽  
Author(s):  
Nir Levy ◽  
David Horn ◽  
Eytan Ruppin
Keyword(s):  
Associative Memory ◽  
Memory Retrieval ◽  
Dendritic Tree ◽  
Distributed Network ◽  
Synaptic Connections ◽  
Object Knowledge ◽  
Dendritic Processing ◽  
Memory Network ◽  
Apical Dendrites ◽  
The Brain

Recent imaging studies suggest that object knowledge is stored in the brain as a distributed network of many cortical areas. Motivated by these observations, we study a multimodular associative memory network, whose functional goal is to store patterns with different coding levels—patterns that vary in the number of modules in which they are encoded. We show that in order to accomplish this task, synaptic inputs should be segregated into intramodular projections and intermodular projections, with the latter undergoing additional nonlinear dendritic processing. This segregation makes sense anatomically if the intermodular projections represent distal synaptic connections on apical dendrites. It is then straightforward to show that memories encoded in more modules are more resilient to focal afferent damage. Further hierarchical segregation of intermodular connections on the dendritic tree improves this resilience, allowing memory retrieval from input to just one of the modules in which it is encoded.

Sign in / Sign up

Export Citation Format

Share Document