How to modify a neural network gradually without changing its input-output functionality

DOI10.1162/NECO.2009.05-08-781MaRDI QIDQ3562856zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Christopher Dimattina, Kechen Zhang

Publication date 28 May 2010

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco.2009.05-08-781

zbMATH Keywords

neural network modeling

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 1843021
• The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks
• Time varying stimulations in simple neural networks and convergence to desired outputs
• Regularization theory in the study of generalization ability of a biological neural network model
• On the properties of input-to-output transformations in neuronal networks

Cites work

• A Simplex Method for Function Minimization
• Approximation by superpositions of a sigmoidal function
• Asymptotic Theory of Information-Theoretic Experimental Design
• Dynamics of Learning Near Singularities in Layered Networks
• Generalized inverses. Theory and applications.
• How Optimal Stimuli for Sensory Neurons Are Constrained by Network Architecture
• scientific article; zbMATH DE number 54240 (Why is no real title available?)
• Modeling inhibition of type II units in the dorsal cochlear nucleus
• Multilayer feedforward networks are universal approximators
• Reconstructing a neural net from its output

Cited in

(3)

• Active data collection for efficient estimation and comparison of nonlinear neural models
• Parameter identifiability in statistical machine learning: a review
• Stochastic collapse: how gradient noise attracts SGD dynamics towards simpler subnetworks

This page was built for publication: How to modify a neural network gradually without changing its input-output functionality

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3562856)