Optimal node perturbation in linear perceptrons with uncertain eligibility trace

DOI10.1016/J.NEUNET.2009.11.013zbMATH Open1396.68095OpenAlexW2017002109WikidataQ51767433 ScholiaQ51767433MaRDI QIDQ1784544FDOQ1784544

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

Publication date: 27 September 2018

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

Full work available at URL: https://doi.org/10.1016/j.neunet.2009.11.013

Recommendations

• Node perturbation learning without noiseless baseline
• Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks
• Synaptic noise as a means of implementing weight-perturbation learning
• Perturbations, optimization, and statistics
• Advanced Lectures on Machine Learning

zbMATH Keywords

uncertaintyresidual errorlearning curvelinear perceptronnode perturbation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Statistical mechanics of learning
• Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks

Cited In (3)

• Node perturbation learning without noiseless baseline
• Synaptic noise as a means of implementing weight-perturbation learning
• Learning Curves for Stochastic Gradient Descent in Linear Feedforward Networks

This page was built for publication: Optimal node perturbation in linear perceptrons with uncertain eligibility trace

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1784544)