Study on Neural Network Integration Method Based on Morphological Associative Memory Framework

An associative memory based on an electronic neural network architecture

IEEE Transactions on Electron Devices ◽

10.1109/t-ed.1987.23118 ◽

1987 ◽

Vol 34 (7) ◽

pp. 1553-1556 ◽

Cited By ~ 35

Author(s):

R.E. Howard ◽

D.B. Schwartz ◽

J.S. Denker ◽

R.W. Epworth ◽

H.P. Graf ◽

...

Keyword(s):

Neural Network ◽

Associative Memory ◽

Network Architecture ◽

Neural Network Architecture

Download Full-text

Robust face recognition from single training image per person via auto-associative memory neural network

2011 International Conference on Electrical and Control Engineering ◽

10.1109/iceceng.2011.6057185 ◽

2011 ◽

Cited By ~ 4

Author(s):

Chuandong Wang ◽

Yanying Yang

Keyword(s):

Neural Network ◽

Face Recognition ◽

Associative Memory ◽

Training Image ◽

Robust Face Recognition

Download Full-text

A Novel Chaotic Neural Network Using Memristive Synapse with Applications in Associative Memory

Abstract and Applied Analysis ◽

10.1155/2012/405739 ◽

2012 ◽

Vol 2012 ◽

pp. 1-19 ◽

Cited By ~ 10

Author(s):

Xiaofang Hu ◽

Shukai Duan ◽

Lidan Wang

Keyword(s):

Neural Network ◽

Associative Memory ◽

Large Scale ◽

Cmos Technology ◽

Chaotic Neural Network ◽

Circuit Element ◽

Nanoscale Cmos ◽

Dynamical Behaviors ◽

Implementation Scheme ◽

Further Development

Chaotic Neural Network, also denoted by the acronym CNN, has rich dynamical behaviors that can be harnessed in promising engineering applications. However, due to its complex synapse learning rules and network structure, it is difficult to update its synaptic weights quickly and implement its large scale physical circuit. This paper addresses an implementation scheme of a novel CNN with memristive neural synapses that may provide a feasible solution for further development of CNN. Memristor, widely known as the fourth fundamental circuit element, was theoretically predicted by Chua in 1971 and has been developed in 2008 by the researchers in Hewlett-Packard Laboratory. Memristor based hybrid nanoscale CMOS technology is expected to revolutionize the digital and neuromorphic computation. The proposed memristive CNN has four significant features: (1) nanoscale memristors can simplify the synaptic circuit greatly and enable the synaptic weights update easily; (2) it can separate stored patterns from superimposed input; (3) it can deal with one-to-many associative memory; (4) it can deal with many-to-many associative memory. Simulation results are provided to illustrate the effectiveness of the proposed scheme.

Download Full-text