A new design method for the complex-valued multistate Hopfield associative memory


Muezzinoglu M., Guzelis C., Zurada J.

IEEE TRANSACTIONS ON NEURAL NETWORKS, cilt.14, sa.4, ss.891-899, 2003 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 14 Sayı: 4
  • Basım Tarihi: 2003
  • Doi Numarası: 10.1109/tnn.2003.813844
  • Dergi Adı: IEEE TRANSACTIONS ON NEURAL NETWORKS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.891-899
  • Anahtar Kelimeler: complex-valued Hopfield network, gray-scale image retrieval, linear inequalities, multistate associative memory, NEURAL NETWORKS, PERCEPTRON
  • Dokuz Eylül Üniversitesi Adresli: Hayır

Özet

A method to store each element of an integral memory set M subset of {1,2,...,K}(n) as a fixed point into a complex-valued multistate Hopfield network is introduced. The method employs a set of inequalities to render each memory pattern as a strict local minimum of a quadratic energy landscape. Based on the solution of this system,. it gives a recurrent network of n multistate neurons with complex and. symmetric synaptic weights, which operates on the finite state space {1, 2,...,K}(n) to minimize this quadratic functional. Maximum number of integral vectors that can be embedded into the energy landscape of the network. by this method is investigated by computer experiments. This paper also enlightens the performance of the proposed method in reconstructing noisy gray-scale images.