The dynamic universality of sigmoidal neural networks

DOI10.1006/inco.1996.0062zbMath0856.68122OpenAlexW2066396564MaRDI QIDQ1923090

Joe Kilian, Hava T. Siegelmann

Publication date: 17 February 1997

Published in: Information and Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/inco.1996.0062

zbMATH Keywords

recurrent neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

An experimental unification of reservoir computing methods, Unnamed Item, The Computational Power of Interactive Recurrent Neural Networks, General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results, Improving Generalization Capabilities of Dynamic Neural Networks, Echo state networks are universal, The ARNN model relativises \(\mathrm{P}=\mathrm{NP}\) and \(\mathrm{P}\neq \mathrm{NP}\), Subrecursive neural networks, Three analog neurons are Turing universal, Design of continuous-time recurrent neural networks with piecewise-linear activation function for generation of prescribed sequences of bipolar vectors, The expressive power of analog recurrent neural networks on infinite input streams, Computational capabilities of analog and evolving neural networks over infinite input streams, Automata complete computation with Hodgkin-Huxley neural networks composed of synfire rings, Analog neuron hierarchy, A survey of computational complexity results in systems and control, Recursive self-organizing network models, Simple Recurrent Networks Learn Context-Free and Context-Sensitive Languages by Counting, Expressive power of first-order recurrent neural networks determined by their attractor dynamics, CONSTRUCTIVE APPROXIMATION BY NEURAL NETWORKS WITH POSITIVE INTEGER WEIGHTS