Neural networks, linear functions and neglected nonlinearity

DOI10.1007/S10287-003-0003-4MaRDI QIDQ2386624zbMATH OpenOpenAlexFDO

Authors Yanyan Li

Publication date 25 August 2005

Published in Computational Management Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10287-003-0003-4

zbMATH Keywords

feedforward neural networksskip-layer connectionsuniversal approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32) Neural networks for/in biological studies, artificial life and related topics (92B20)

Review text

The article focuses on the ability of feedforward networks to approximate a linear function. By means of MAPLE empirical experiments one justifies the following statement: neural networks can represent linear functions without the need for skip-layer connections. In case skip-layer formulation is used, there are potential problems in separating linear and nonlinear components. Statistical tests with neural networks make use of these issues.

Recommendations

• Publication:4943029
• Bounds on the complexity of neural‐network models and comparison with linear methods
• scientific article; zbMATH DE number 1286423
• scientific article; zbMATH DE number 1545336
• A counterexample regarding ``New study on neural networks: the essential order of approximation

Cited in

(5)

• Linear neural networks revisited: from PageRank to family happiness
• Linearized two-layers neural networks in high dimension
• scientific article; zbMATH DE number 1432156 (Why is no real title available?)
• scientific article; zbMATH DE number 7745105 (Why is no real title available?)
• Neural networks and seasonality: Some technical considerations

Describes a project that uses

Uses Software

• Maple

This page was built for publication: Neural networks, linear functions and neglected nonlinearity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2386624)