Rational approximation techniques for analysis of neural networks

DOI10.1109/18.312168zbMath0811.94041OpenAlexW2134974549MaRDI QIDQ4308779

Kai-Yeung Siu, Thomas Kailath, Vwani P. Roychowdhury

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 networksBoolean functionsharmonic analysisrational approximationparitythreshold circuitsmultilayer neural networkssigmoidal networks

Mathematics Subject Classification ID

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

Related Items (13)

Size and Energy of Threshold Circuits Computing Mod Functions ⋮ Breaking the Minsky--Papert Barrier for Constant-Depth Circuits ⋮ General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results ⋮ The Power of Asymmetry in Constant-Depth Circuits ⋮ A small decrease in the degree of a polynomial with a given sign function can exponentially increase its weight and length ⋮ Energy and depth of threshold circuits ⋮ Size-energy tradeoffs for unate circuits computing symmetric Boolean functions ⋮ Algorithmic Polynomials ⋮ Negative results for approximation using single layer and multilayer feedforward neural networks ⋮ A size-depth trade-off for the analog computation of Boolean functions ⋮ Optimal bounds for sign-representing the intersection of two halfspaces by polynomials ⋮ Near-Optimal Lower Bounds on the Threshold Degree and Sign-Rank of AC$^0$ ⋮ Average-Case Lower Bounds and Satisfiability Algorithms for Small Threshold Circuits

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