STDP-Compatible Approximation of Backpropagation in an Energy-Based Model

DOI10.1162/NECO_a_00934zbMath1414.92007WikidataQ48008151 ScholiaQ48008151MaRDI QIDQ5380662

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

Publication date: 6 June 2019

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

zbMATH Keywords

backpropagationneural computationspike-timing-dependent plasticityenergy-based modelLangevin Markov chain Monte Carlo inference

Mathematics Subject Classification ID

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

Related Items

Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review, On the Algorithmic Power of Spiking Neural Networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Phenomenological models of synaptic plasticity based on spike timing
• An introduction to MCMC for machine learning
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Equivalence of Equilibrium Propagation and Recurrent Backpropagation
• A Connection Between Score Matching and Denoising Autoencoders
• Neurons with graded response have collective computational properties like those of two-state neurons.