Neural networks using a logistics sigmoid function: linear classifier bounds and global nonattainability

DOI10.1080/02331939508844055MaRDI QIDQ4764604zbMATH OpenOpenAlexFDO

Authors Jiming Liu, Anthony V. Fiacco

Publication date 8 May 1995

Published in Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/02331939508844055

zbMATH Keywords

neural networksmean-square erroroptimal value boundsnonattainabilitysolution attainability

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Mathematical programming (90C99)

Recommendations

• The computational intractability of training sigmoidal neural networks
• An unfeasibility view of neural network learning
• Computational limitations on training sigmoid neural networks
• Training a Single Sigmoidal Neuron Is Hard

Cited in

(1)

• Solution Existence Theory for Artificial Neural Networks

This page was built for publication: Neural networks using a logistics sigmoid function: linear classifier bounds and global nonattainability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4764604)