Open AccessNeural computation by concentrating information in time.
Author(s) -
David W. Tank,
J. J. Hopfield
Publication year - 1987
Publication title -
proceedings of the national academy of sciences of the united states of america
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 5.011
H-Index - 771
eISSN - 1091-6490
pISSN - 0027-8424
DOI - 10.1073/pnas.84.7.1896
Subject(s) - computer science , artificial neural network , computation , stimulus (psychology) , set (abstract data type) , time delay neural network , models of neural computation , activation function , focus (optics) , artificial intelligence , algorithm , psychology , physics , optics , psychotherapist , programming language
An analog model neural network that can solve a general problem of recognizing patterns in a time-dependent signal is presented. The networks use a patterned set of delays to collectively focus stimulus sequence information to a neural state at a future time. The computational capabilities of the circuit are demonstrated on tasks somewhat similar to those necessary for the recognition of words in a continuous stream of speech. The network architecture can be understood from consideration of an energy function that is being minimized as the circuit computes. Neurobiological mechanisms are known for the generation of appropriate delays.