Holographic associative memory

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Holographic Associative Memory is part of the family of analog, correlation-based, associative, stimulus-response memories, where information is mapped onto the phase orientation of complex numbers operating. It can be considered as a complex valued artificial neural network. The holographic associative memory exhibits some remarkable characteristics. Holographs have been shown to be effective for associative memory tasks, generalization, and pattern recognition with changeable attention. Ability of dynamic search localization is central to natural memory. For example, in visual perception, humans always tend to focus on some specific objects in a pattern. Humans can effortlessly change the focus from object to object without requiring relearning. It provides a computational model which can mimic this ability by creating representation for focus. At the heart of this new memory lies a novel bi-modal representation of pattern and a hologram-like complex spherical weight state-space. Besides the usual advantages of associative computing, this technique also has excellent potential for fast optical realization because the underlying hyper-spherical computations can be naturally implemented on optical computations.

See also[edit]


  • Sutherland, J., Holographic Models of Memory, Learning and Expression, International J. of Neural Systems, 1(3), 1990, pp356–267
  • J. I. Khan. Attention Modulated Associative Computing and Content-Associative Search in Image Archive. PhD thesis, University of Hawaii, August 1995.
  • K. I. Khan and D. Y. Yun. Characteristics of Multidimensional Holographic Associative Memory in Retrieval with Dynamically Localizable Attention. IEEE Transactions on Neural Networks, 9(3):389–406, May 1998.
  • HE Michel, AAS Awwal, Enhanced artificial neural networks using complex numbers, Neural Networks, 1999. Proceedings. 1999 IEEE International Joint Conference on
  • R Stoop, J Buchli, G Keller, WH Steeb, Stochastic resonance in pattern recognition by a holographic neuron model, Physical Review E, 2003.
  • Y Hendra, RP Gopalan, MG Nair, A method for dynamic indexing of large image databases, Systems, Man, and Cybernetics, 1999. IEEE SMC'99.
  • HE Michel, S Kunjithapatham, Processing Landsat TM data using complex-valued neural networks, Proceedings of SPIE, the International Society for Optical, 2002.
  • RP Gopalan, G Lee, Indexing of Image Databases Using Untrained 4D Holographic Memory Model, 15th Australian Joint Conference on Artificial Intelligence, - Springer Page 1. RI McKay and J. Slaney (Eds.): AI 2002, LNAI 2557, pp. 237–248.
  • RWTH Aachen, IH Ney, Approaches to Invariant Image Object Recognition, [1]