Rational approximation techniques for analysis of neural networks
From MaRDI portal
Publication:4308779
DOI10.1109/18.312168zbMath0811.94041MaRDI 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
neural networks; Boolean functions; harmonic analysis; rational approximation; parity; threshold circuits; multilayer neural networks; sigmoidal networks
41A20: Approximation by rational functions
94C05: Analytic circuit theory
41A30: Approximation by other special function classes
65T99: Numerical methods in Fourier analysis
Related Items
Breaking the Minsky--Papert Barrier for Constant-Depth Circuits, The Power of Asymmetry in Constant-Depth Circuits, Average-Case Lower Bounds and Satisfiability Algorithms for Small Threshold Circuits, General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results, Near-Optimal Lower Bounds on the Threshold Degree and Sign-Rank of AC$^0$, Algorithmic Polynomials, Optimal bounds for sign-representing the intersection of two halfspaces by polynomials, 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, A size-depth trade-off for the analog computation of Boolean functions, Negative results for approximation using single layer and multilayer feedforward neural networks, Size and Energy of Threshold Circuits Computing Mod Functions