Node perturbation learning without noiseless baseline

DOI10.1016/J.NEUNET.2010.12.001MaRDI QIDQ553265zbMATH OpenOpenAlexWikidataFDO

Authors Tatsuya Cho, Kentaro Katahira, Kazuo Okanoya, Masato Okada

Publication date 26 July 2011

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2010.12.001

zbMATH Keywords

learning curvelinear perceptronnode perturbationnoiseless baselinestochastic gradient method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Learning with noise in a linear perceptron
• Learning nested differences in the presence of malicious noise
• Learning nested differences in the presence of malicious noise
• Optimal node perturbation in linear perceptrons with uncertain eligibility trace
• scientific article; zbMATH DE number 1708093
• scientific article; zbMATH DE number 1453040
• Regularized greedy algorithms for network training with data noise

Cites work

• Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks
• Optimal node perturbation in linear perceptrons with uncertain eligibility trace
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Statistical mechanics of learning

Cited in

(2)

• Optimal node perturbation in linear perceptrons with uncertain eligibility trace
• Synaptic noise as a means of implementing weight-perturbation learning

This page was built for publication: Node perturbation learning without noiseless baseline

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q553265)