A Bound on the Precision Required to Estimate a Boolean Perceptron from Its Average Satisfying Assignment

DOI10.1137/S0895480103426765MaRDI QIDQ3440259zbMATH OpenFDO

Authors Paul W. Goldberg

Publication date 22 May 2007

Published in SIAM Journal on Discrete Mathematics (Search for Journal in Brave)

zbMATH Keywords

geometryBoolean functionsinductive learningthreshold functions

Mathematics Subject Classification ID

Computational learning theory (68Q32) Lattices and convex bodies in (n) dimensions (aspects of discrete geometry) (52C07) Arrangements of points, flats, hyperplanes (aspects of discrete geometry) (52C35) Complexity classes (hierarchies, relations among complexity classes, etc.) (68Q15)

Recommendations

• scientific article; zbMATH DE number 1827089
• scientific article; zbMATH DE number 1966612
• A Uniform Lower Bound on Weights of Perceptrons
• Bounds on the number of units for computing arbitrary dichotomies by multilayer perceptrons
• Probabilistic lower bounds for approximation by shallow perceptron networks
• Learning of bounded-weight Boolean functions
• A lower bound for perceptrons and an oracle separation of the \(PP^{PH}\) hierarchy
• Estimating the efficiency of threshold representations of Boolean functions
• Bounds for the number of Boolean functions admitting affine approximations of a given accuracy
• A note on a priori estimations of classification circuit complexity

Cited in

(3)

• scientific article; zbMATH DE number 1827089 (Why is no real title available?)
• Testing (Subclasses of) Halfspaces
• Improved approximation of linear threshold functions

This page was built for publication: A Bound on the Precision Required to Estimate a Boolean Perceptron from Its Average Satisfying Assignment

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3440259)