Bounds for the Computational Power and Learning Complexity of Analog Neural Nets

DOI10.1137/S0097539793256041MaRDI QIDQ4337641zbMATH OpenOpenAlexFDO

Authors Wolfgang Maass

Publication date 26 May 1997

Published in SIAM Journal on Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/s0097539793256041

zbMATH Keywords

neural networkscircuit complexitythreshold circuitslearning complexityanalog computing

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Complexity classes (hierarchies, relations among complexity classes, etc.) (68Q15) Analytic circuit theory (94C05)

Recommendations

• scientific article; zbMATH DE number 774001
• Rational approximation techniques for analysis of neural networks
• Discrete mathematics of neural networks. Selected topics

Cited in

(12)

• scientific article; zbMATH DE number 773997 (Why is no real title available?)
• scientific article; zbMATH DE number 7250146 (Why is no real title available?)
• scientific article; zbMATH DE number 774001 (Why is no real title available?)
• The descriptive complexity of graph neural networks
• Piecewise-Linear Neural Networks and Their Relationship to Rule Extraction from Data
• Rational approximation techniques for analysis of neural networks
• General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
• Stronger connections between circuit analysis and circuit lower bounds, via PCPs of proximity
• Discrete mathematics of neural networks. Selected topics
• Computing with discrete multi-valued neurons
• Analog computation via neural networks
• Monotone learning with rectified wire networks

This page was built for publication: Bounds for the Computational Power and Learning Complexity of Analog Neural Nets

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4337641)