STDP-compatible approximation of backpropagation in an energy-based model

DOI10.1162/NECO_A_00934MaRDI QIDQ5380662zbMATH OpenDBLPWikidataFDO

Authors Yoshua Bengio, Thomas Mesnard, Asja Fischer, Saizheng Zhang, Yuhuai Wu

Publication date 6 June 2019

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/NECO_A_00934

zbMATH Keywords

backpropagationenergy-based modelLangevin Markov chain Monte Carlo inferenceneural computationspike-timing-dependent plasticity

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

• An approximation of the error backpropagation algorithm in a predictive coding network with local Hebbian synaptic plasticity
• Spike-Timing Error Backpropagation in Theta Neuron Networks
• Predictive coding approximates backprop along arbitrary computation graphs
• Bayesian Spiking Neurons II: Learning
• Error-backpropagation in temporally encoded networks of spiking neurons

Cites work

• A Connection Between Score Matching and Denoising Autoencoders
• An introduction to MCMC for machine learning
• Equivalence of equilibrium propagation and recurrent backpropagation
• scientific article; zbMATH DE number 6982943 (Why is no real title available?)
• Neurons with graded response have collective computational properties like those of two-state neurons
• Phenomenological models of synaptic plasticity based on spike timing
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
• What regularized auto-encoders learn from the data-generating distribution

Cited in

(5)

• Equivalence of equilibrium propagation and recurrent backpropagation
• Predictive coding approximates backprop along arbitrary computation graphs
• On the Algorithmic Power of Spiking Neural Networks
• An approximation of the error backpropagation algorithm in a predictive coding network with local Hebbian synaptic plasticity
• Deep convolutional neural networks for image classification: a comprehensive review

This page was built for publication: STDP-compatible approximation of backpropagation in an energy-based model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380662)