Autoassociative neural memory capacity and dynamics

Storage capacity and retrieval dynamics of autoassociative neural memories (ANMs) are investigated. An associative memory capacity measure based on the memory's performance versus the number of stored memory vectors (where performance is defined in terms of the memory's error-correcting ability and its fundamental memories' attraction volumes) is introduced. The proposed capacity/performance measure has been tested for several ANMs having the same dynamic Hopfield-memory-like architecture, each using a different recording technique. Correlation, generalized inverse (orthogonal), and Ho-Kashyap memory recordings have been investigated. Monte Carlo analysis has been performed on ANMs recorded with randomly generated patterns in order to determine and compare performance characteristics and retrieval dynamics

[1]  B V Kumar,et al.  Evaluation of the use of the Hopfield neural network model as a nearest-neighbor algorithm. , 1986, Applied optics.

[2]  Shun-ichi Amari,et al.  Statistical neurodynamics of associative memory , 1988, Neural Networks.

[3]  Teuvo Kohonen,et al.  Correlation Matrix Memories , 1972, IEEE Transactions on Computers.

[4]  Shun-ichi Amari,et al.  Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements , 1972, IEEE Transactions on Computers.

[5]  János Komlós,et al.  Convergence results in an associative memory model , 1988, Neural Networks.

[6]  Mohamad H. Hassoun.  Dynamic heteroassociative neural memories , 1989, Neural Networks.

[7]  Mohamad H. Hassoun.  Adaptive Dynamic Heteroassociative Neural Memories For Pattern Classification , 1989, Photonics West - Lasers and Applications in Science and Engineering.

[8]  J. Keeler.  Information capacity of outer-product neural networks , 1987 .

[9]  L. Personnaz,et al.  Collective computational properties of neural networks: New learning mechanisms. , 1986, Physical review. A, General physics.

[10]  Gérard Weisbuch,et al.  Scaling laws for the attractors of Hopfield networks , 1985 .

[11]  Yaser S. Abu-Mostafa,et al.  Information capacity of the Hopfield model , 1985, IEEE Trans. Inf. Theory.

[12]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[13]  R J Marks Ii,et al.  Synchronous vs asynchronous behavior of Hopfield's CAM neural net. , 1987, Applied optics.

[14]  Mohamad H. Hassoun,et al.  High Performance Recording Algorithm For Hopfield Model Associative Memories , 1989 .

[15]  Kaoru Nakano,et al.  Associatron-A Model of Associative Memory , 1972, IEEE Trans. Syst. Man Cybern..

[16]  Stephen A. Ritz,et al.  Distinctive features, categorical perception, and probability learning: some applications of a neural model , 1977 .

[17]  Sompolinsky,et al.  Storing infinite numbers of patterns in a spin-glass model of neural networks. , 1985, Physical review letters.

[18]  Santosh S. Venkatesh,et al.  The capacity of the Hopfield associative memory , 1987, IEEE Trans. Inf. Theory.

[19]  Teuvo Kohonen,et al.  Representation of Associated Data by Matrix Operators , 1973, IEEE Transactions on Computers.

[20]  James A. Anderson,et al.  A simple neural network generating an interactive memory , 1972 .

[21]  Gardiner S. Stiles,et al.  A Quantitative Comparison of the Performance of Three Discrete Distributed Associative Memory Models , 1987, IEEE Transactions on Computers.