A No-Go Theorem for One-Layer Feedforward Networks

DOI10.1162/NECO_a_00657zbMath1416.92012arXiv1310.3796OpenAlexW1977368668WikidataQ48589737 ScholiaQ48589737MaRDI QIDQ5383800

Vladimir Itskov, Chad Giusti

Publication date: 20 June 2019

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

Full work available at URL: https://arxiv.org/abs/1310.3796

zbMATH Keywords

combinatorial codesone-layer feedforward neural networks

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Combinatorial codes (94B25)

Related Items (16)

Nondegenerate Neural Codes and Obstructions to Closed-Convexity ⋮ Non-monotonicity of closed convexity in neural codes ⋮ Signless normalized Laplacian for hypergraphs ⋮ What can topology tell us about the neural code? ⋮ Neural codes with three maximal codewords: convexity and minimal embedding dimension ⋮ Minimal embedding dimensions of connected neural codes ⋮ Error-correcting codes and neural networks ⋮ Algebraic signatures of convex and non-convex codes ⋮ Wheels: a new criterion for non-convexity of neural codes ⋮ Neural Ring Homomorphisms and Maps Between Neural Codes ⋮ Hyperplane Neural Codes and the Polar Complex ⋮ On open and closed convex codes ⋮ Neural Codes, Decidability, and a New Local Obstruction to Convexity ⋮ Obstructions to convexity in neural codes ⋮ What Makes a Neural Code Convex? ⋮ Morphisms of Neural Codes

Cites Work

• Unnamed Item
• Unnamed Item
• The neural ring: an algebraic tool for analyzing the intrinsic structure of neural codes
• Nerves of simplicial complexes
• Intersection Patterns of Convex Sets via Simplicial Complexes: A Survey
• On Dedekind's Problem: The Number of Isotone Boolean Functions. II
• Approximation by superpositions of a sigmoidal function

This page was built for publication: A No-Go Theorem for One-Layer Feedforward Networks