The Stochastic Delta Rule: Faster and More Accurate Deep Learning Through Adaptive Weight Noise

DOI10.1162/neco_a_01276zbMath1468.68181OpenAlexW3012024403WikidataQ90425748 ScholiaQ90425748MaRDI QIDQ5131130

Noah Frazier-Logue, Stephen José Hanson

Publication date: 2 November 2020

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

Full work available at URL: https://doi.org/10.1162/neco_a_01276

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (2)

Enhancing threshold neural network via suprathreshold stochastic resonance for pattern classification ⋮ Training threshold neural networks by extreme learning machine and adaptive stochastic resonance

Uses Software

• darch
• CIFAR
• PyTorch
• ImageNet
• GitHub
• GPipe
• EfficientNet

Cites Work

• The dropout learning algorithm
• Reducing the Dimensionality of Data with Neural Networks
• Unnamed Item

This page was built for publication: The Stochastic Delta Rule: Faster and More Accurate Deep Learning Through Adaptive Weight Noise