Key and recollection vector effects on heteroassociative memory performance.

Most associative memory work has concentrated on autoassociative memories (AAMs). These associative processors provide reduced noise and error correction in their output data. We will consider heteroassociative memories (HAMs), which are needed to provide decisions on the class of the input data and inferences for subsequent processing. We derive new equations for the storage capacity and noise performance of HAMs, emphasize how they differ from those derived for AAMs, suggest new performance measures to be used, and show how different recollection vector encodings can improve HAM performance.

[1]  James A. Anderson,et al.  Cognitive and psychological computation with neural models , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  D Casasent,et al.  Frequency-multiplexed and pipelined iterative optical systolic array processors. , 1983, Applied optics.

[3]  Y Owechko,et al.  Optoelectronic resonator neural networks. , 1987, Applied optics.

[4]  David Casasent,et al.  Distortion-Invariant Associative Memories And Processors , 1986, Optics & Photonics.

[5]  D Casasent,et al.  Error-correction coding in an associative processor. , 1987, Applied optics.

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

[7]  Demetri Psaltis,et al.  A space integrating acousto-optic matrix-matrix multiplier , 1984 .

[8]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[9]  G. J. Dunning,et al.  Holographic associative memory with nonlinearities in the correlation domain. , 1987, Applied optics.

[10]  David Casasent.  Scene Analysis Research: Optical Pattern Recognition And Artificial Intelligence , 1986, Other Conferences.

[11]  Demetri Psaltis,et al.  Nonlinear discriminant functions and associative memories , 1987 .

[12]  C. R. Rao,et al.  Generalized Inverse of Matrices and its Applications , 1972 .

[13]  Gardiner S. Stiles,et al.  On the Effect of Noise on the Moore-Penrose Generalized Inverse Associative Memory , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  D Casasent,et al.  Unified synthetic discriminant function computational formulation. , 1984, Applied optics.

[15]  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.

[16]  D Psaltis,et al.  Optical information processing based on an associative-memory model of neural nets with thresholding and feedback. , 1985, Optics letters.

[17]  D P Casasent,et al.  Space and frequency-multiplexed optical linear algebra processor: fabrication and initial tests. , 1986, Applied optics.

[18]  M. J. Little,et al.  Enhanced Memory Capacity Of A Hopfield Neural Network , 1986, Optics & Photonics.

[19]  D Psaltis,et al.  Storage capacity of holographic associative memories. , 1986, Optics letters.

[20]  David Casasent,et al.  Associative Memory Synthesis, Performance, Storage Capacity And Updating: New Heteroassociative Memory Results , 1988, Other Conferences.

[21]  J. Austin.  Associative memory , 1987 .

[22]  David Casasent.  Optical pattern recognition and artificial intelligence , 1986 .

[23]  Tsunehiro Aibara,et al.  An Improvement on the Moore-Penrose Generalized Inverse Associative Memory , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[24]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

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

[26]  J N Lee,et al.  Optical implementations of associative networks with versatile adaptive learning capabilities. , 1987, Applied optics.