Non-Holographic Associative Memory

  title={Non-Holographic Associative Memory},
  author={D. Willshaw and O. Buneman and H. Longuet-Higgins},
The features of a hologram that commend it as a model of associative memory can be improved on by other devices. 

Topics from this paper

Holographic associative memory for word-break recognition.
A holographic associative memory is described that is able to identify individual words and insert word breaks in a concatenated word string and is shift invariant and has error-correction capability. Expand
Adaptive 2D Holographic Associative Processor
  • M. S. Kim, C. Guest
  • Computer Science, Engineering
  • Photonics West - Lasers and Applications in Science and Engineering
  • 1986
An architecture and operating system that accommodates the requirements of fuzzy cognitive maps while utilizing the capabilities of photorefractive holography are presented. Expand
An Adaptive Associative Memory Principle
  • T. Kohonen
  • Computer Science
  • IEEE Transactions on Computers
  • 1974
It is shown that an analog associative memory with optimal selectivity can be formed in adaptive processes which use learning algorithms related to the gradient method. The information is distributedExpand
The Quantum Binding Problem in the Context of Associative Memory
The binding problem is solved by mapping the information representing different objects into superposition by using entanglement and Grover's amplification algorithm for the retrieval of associations from associative memory during visual scene analysis. Expand
Fault-Tolerance in Non-linear Neural Networks
Among the models of parallel computing architectures of neural networks, the model of distributed associative memory has very promising features including fault tolerance.
Optical holography as an analogue for a neural reuse mechanism 1
Abstract We propose an analogy between optical holography and neural behavior as a hypothesis about the physical mechanisms of neural reuse. Specifically, parameters in optical holography (frequency,Expand
Enhancing the storage capacity of binary associative memories
  • W. Fellenz, John G. Taylor
  • Computer Science
  • IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)
  • 1999
It is shown that the hidden layer associative network is less dependent on the number of ones in the storage patterns and shows an improved retrieval capacity from incomplete retrieval patterns. Expand
Incoherent optical associative memory by using synthetic discriminant function filters.
A new associative memory system applying incoherent correlators is presented, which is composed of a nonlinear processor and optical-electronic feedback loop and can be recalled without cross talk, to realize a high association ability and stable operation. Expand
Learning in neural network memories
Various algorithms for constructing a synaptic coupling matrix which can associatively map input patterns onto nearby stored memory patterns are reviewed. Issues discussed include performance,Expand
Some General Problems of Memory
It is shown that a Fourier series provides an interesting analogy for the distributed property of memory and the question is discussed of whether memory is stored in a discrete or continuous parametrization. Expand


Holographic Model of Temporal Recall
  • D. Gabor
  • Computer Science, Medicine
  • Nature
  • 1968
It is shown that there is at least one other mathematical model, which is considered to be a closer analogue of holography, because it operates with triple products of the temporal function to be recognized or recalled. Expand
Improved Holographic Model of Temporal Recall
  • D. Gabor
  • Computer Science, Medicine
  • Nature
  • 1968
The modified static system described here is an alternative to Longuet-Higgins' model and takes account of the weaknesses of the nervous system as well as of its powers to imitate human memory with models. Expand
Theory of Optical Information Storage in Solids
The theory of three-dimensional optical storage lends support to Beurle’s proposed mechanism of information storage in the brain, and makes three- dimensional storage very suitable for associative memories. Expand
The classification of modifiable synapses and their use in models for conditioning
  • G. Brindley
  • Psychology
  • Proceedings of the Royal Society of London. Series B. Biological Sciences
  • 1967
Modifiable synapses are analysed theoretically. It is proved that they fall into three classes (called A, B and C), such that any two members of the same class can, with the aid of non-rememberingExpand
The neurophysiology of remembering.
  • K. Pribram
  • Physics, Medicine
  • Scientific American
  • 1969