Accession Number : ADA257019


Title :   Dynamics of Analog Electronic Neural Networks


Descriptive Note : Final rept. Jun 1989-Jun 1992


Corporate Author : HARVARD UNIV CAMBRIDGE MA


Personal Author(s) : Waugh, Frederick R


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a257019.pdf


Report Date : 31 Aug 1992


Pagination or Media Count : 11


Abstract : We review recent results on dynamics and stability of analog neural networks and discuss their application to associative memory and visual processing. Stability criteria for these networks, gaurantee convergence to fixed-point attractors under continuous-time and discrete-time, parallel updating. For associative memory, phase diagrams describing different attractor types are discussed, and it is shown that reducing analog transfer function steepness improves network performance. For visual processing, a two- dimensional, translation-invariant network is described. The network detects image features using a novel architecture that greatly reduces network wiring. Neural networks, Associative memory, Feature detection, Image processing, Analog computation.


Descriptors :   *NEURAL NETS , *ANALOG COMPUTERS , IMAGE PROCESSING , FUNCTIONS , DETECTION , DYNAMICS , PROCESSING , TIME , CONVERGENCE , TRANSLATIONS , DIAGRAMS , PHASE DIAGRAMS , ARCHITECTURE , TRANSFER , ANALOGS , IMAGES , PHASE , TWO DIMENSIONAL , NETWORKS , TRANSFER FUNCTIONS , STABILITY


Subject Categories : Computer Systems
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE