Shattering All Sets of ‘k’ Points in “General Position” Requires (k — 1)/2 Parameters

DOI10.1162/neco.1997.9.2.337zbMath0869.68087OpenAlexW2009770446MaRDI QIDQ3125238

Eduardo D. Sontag

Publication date: 18 March 1997

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco.1997.9.2.337

zbMATH Keywords

neural networkspiecewise-analytic functions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

Elimination of constants from machines over algebraically closed fields ⋮ Some new maximum VC classes ⋮ On the relevance of time in neural computation and learning

Cites Work

• Feedforward nets for interpolation and classification
• Critical points for least-squares problems involving certain analytic functions, with applications to sigmoidal nets
• Lower Bounds for the Computational Power of Networks of Spiking Neurons

This page was built for publication: Shattering All Sets of ‘k’ Points in “General Position” Requires (k — 1)/2 Parameters