Rational approximation techniques for analysis of neural networks

DOI10.1109/18.312168MaRDI QIDQ4308779zbMATH OpenOpenAlexFDO

Authors Kai-Yeung Siu, Vwani Roychowdhury, T. Kailath

Publication date 4 May 1995

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/18.312168

zbMATH Keywords

neural networksharmonic analysisBoolean functionsparityrational approximationthreshold circuitsmultilayer neural networkssigmoidal networks

Mathematics Subject Classification ID

Approximation by other special function classes (41A30) Analytic circuit theory (94C05) Approximation by rational functions (41A20) Numerical methods in Fourier analysis (65T99)

Recommendations

• Approximating threshold circuits by rational functions
• Bounds for the Computational Power and Learning Complexity of Analog Neural Nets
• Publication:4868351
• Approximation and estimation bounds for artificial neural networks
• Scientific article; zbMATH DE number 1843047

Cited in

(16)

• General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
• Energy and depth of threshold circuits
• Signalling techniques and their effect on neural network implementation sizes
• Average-case lower bounds and satisfiability algorithms for small threshold circuits
• Breaking the Minsky--Papert Barrier for Constant-Depth Circuits
• Negative results for approximation using single layer and multilayer feedforward neural networks
• Size and Energy of Threshold Circuits Computing Mod Functions
• Algorithmic Polynomials
• A small decrease in the degree of a polynomial with a given sign function can exponentially increase its weight and length
• A size-depth trade-off for the analog computation of Boolean functions
• Neural networks and Boolean functions
• Size-energy tradeoffs for unate circuits computing symmetric Boolean functions
• Near-Optimal Lower Bounds on the Threshold Degree and Sign-Rank of AC$^0$
• A linear relation between input and first layer in neural networks
• The power of asymmetry in constant-depth circuits
• scientific article; zbMATH DE number 773997 (Why is no real title available?)

This page was built for publication: Rational approximation techniques for analysis of neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4308779)