arXiv:cond-mat/9710010AbstractReferencesReviewsResources
Limit cycles of a perceptron
Published 1997-10-01, updated 1997-12-11Version 2
An artificial neural network can be used to generate a series of numbers. A boolean perceptron generates bit sequences with a periodic structure. The corresponding spectrum of cycle lengths is investigated analytically and numerically; it has similarities with properties of rational numbers.
Comments: LaTeX and 4 postscript pages of figures
Categories: cond-mat.dis-nn
Keywords: limit cycles, boolean perceptron generates bit sequences, artificial neural network, cycle lengths, rational numbers
Tags: journal article
Related articles: Most relevant | Search more
arXiv:cond-mat/0006486 (Published 2000-06-30)
Forecasting price increments using an artificial Neural Network
arXiv:2104.05402 [cond-mat.dis-nn] (Published 2021-03-06)
Artificial neural network as a universal model of nonlinear dynamical systems
arXiv:1906.11216 [cond-mat.dis-nn] (Published 2019-06-26)
Finding Quantum Many-Body Ground States with Artificial Neural Network