A Learning Framework for Winner-Take-All Networks with Stochastic Synapses

DOI10.1162/neco_a_01080zbMath1480.92015arXiv1708.04251OpenAlexW2963569875WikidataQ52322425 ScholiaQ52322425MaRDI QIDQ5157187

Gert Cauwenberghs, Hesham Mostafa

Publication date: 12 October 2021

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

Full work available at URL: https://arxiv.org/abs/1708.04251

zbMATH Keywords

neural networksintegrate-and-fire neuronsstochastic synapsesWTA networks

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Regularization by noise (60H50)

Uses Software

• Theano
• Adam
• NEST
• SpiNNaker

Cites Work

• Unnamed Item
• Learning in the machine: random backpropagation and the deep learning channel
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Training Products of Experts by Minimizing Contrastive Divergence
• Bayesian Spiking Neurons I: Inference
• Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network
• Rhythmic Inhibition Allows Neural Networks to Search for Maximally Consistent States

This page was built for publication: A Learning Framework for Winner-Take-All Networks with Stochastic Synapses