On the computational efficiency of symmetric neural networks

DOI10.1016/0304-3975(91)90394-HzbMATH Open0745.68044OpenAlexW2040867457MaRDI QIDQ1176243FDOQ1176243

Authors: Jiří Wiedermann 

Publication date: 25 June 1992

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0304-3975(91)90394-h

Recommendations

• scientific article; zbMATH DE number 17830
• scientific article; zbMATH DE number 4201667
• Symmetric discrete universal neural networks
• Continuous-Time Symmetric Hopfield Nets Are Computationally Universal
• Continuous-Time Symmetric Hopfield Nets Are Computationally Universal

zbMATH Keywords

neural networks

Mathematics Subject Classification ID

Cites Work

• Title not available (Why is that?)
• Neural networks and physical systems with emergent collective computational abilities
• Title not available (Why is that?)
• Neurons with graded response have collective computational properties like those of two-state neurons
• Alternation
• ``Neural computation of decisions in optimization problems
• Parallel computation with threshold functions
• Title not available (Why is that?)
• Constant Depth Reducibility

Cited In (9)

• Computational differences between asymmetrical and symmetrical networks
• Neural networks as systems for recognizing patterns
• Title not available (Why is that?)
• Stability and looping in connectionist models with asymmetric weights
• Title not available (Why is that?)
• Antisymmetrical neural networks
• Approximation of continuous functions of several variables by an arbitrary nonlinear continuous function of one variable, linear functions, and their superpositions
• A trade-off formula in designing asymmetric neural networks
• High-speed division unit using asymmetric neural network architecture

This page was built for publication: On the computational efficiency of symmetric neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1176243)