Premium
Dynamics and neural network computation
Author(s) -
Hopfield J. J.
Publication year - 1990
Publication title -
international journal of quantum chemistry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.484
H-Index - 105
eISSN - 1097-461X
pISSN - 0020-7608
DOI - 10.1002/qua.560382461
Subject(s) - computation , artificial neural network , computer science , state (computer science) , reservoir computing , function (biology) , models of neural computation , mode (computer interface) , theoretical computer science , recurrent neural network , artificial intelligence , algorithm , evolutionary biology , biology , operating system
Computation is carried out by the motion of the state of a dynamical system. This description unites digital and “neural network” computation. The use of an energy function to understand and to program batch mode computation on feedback networks is reviewed. Recognizing words in continuous speech illustrates the use of a compound network to solve a real‐world problem where data arrive continuously over time. A new tool, a Lagrangian formulation, is introduced for studying networks which oscillate, and as a means for formulating problems which need to optimize functional integrals.