The dropout learning algorithm

DOI10.1016/j.artint.2014.02.004zbMath1333.68225OpenAlexW2164370980WikidataQ38915847 ScholiaQ38915847MaRDI QIDQ490652

Peter Sadowski, Pierre Baldi

Publication date: 27 August 2015

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2014.02.004

zbMATH Keywords

regularizationneural networksgeometric meanbackpropagationmachine learningvariance minimizationstochastic gradient descentensemblesparse representationsstochastic neurons

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (13)

Comments on: ``A random forest guided tour ⋮ On better training the infinite restricted Boltzmann machines ⋮ Global optimization issues in deep network regression: an overview ⋮ Learning in the machine: random backpropagation and the deep learning channel ⋮ Learning in the machine: the symmetries of the deep learning channel ⋮ Deep Learning in the Natural Sciences: Applications to Physics ⋮ Dropout training for SVMs with data augmentation ⋮ The Stochastic Delta Rule: Faster and More Accurate Deep Learning Through Adaptive Weight Noise ⋮ Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review ⋮ Learning in the machine: to share or not to share? ⋮ Unnamed Item ⋮ Surprising properties of dropout in deep networks ⋮ Adaptive infinite dropout for noisy and sparse data streams

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bagging predictors
• A derivative-coderivative inclusion in second-order nonsmooth analysis
• A new refinement of the arithmetic mean -- geometric mean inequality
• Refined arithmetic, geometric and harmonic mean inequalities
• Sharp bounds for the difference between the arithmetic and geometric means
• Generalization of an inequality of Ky Fan
• Selfimprovemvent of the inequality between arithmetic and geometric means
• Sequential updating of conditional probabilities on directed graphical structures
• A Refinement of the Arithmetic Mean-Geometric Mean Inequality
• Some inequalities for arithmetic and geometric means
• On the Ky Fan inequality and related inequalities I
• Learning representations by back-propagating errors
• Advanced Lectures on Machine Learning
• Probability and Computing
• On the Ky Fan inequality and related inequalities II
• Improved upper and lower bounds for the difference \(A_n-G_n\)

This page was built for publication: The dropout learning algorithm