Surprising properties of dropout in deep networks

zbMath1469.68099arXiv1602.04484MaRDI QIDQ4558527

Philip M. Long, David P. Helmbold

Publication date: 22 November 2018

Full work available at URL: https://arxiv.org/abs/1602.04484

zbMATH Keywords

regularizationlearning theorydropoutdeep neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items (1)

Dropout fails to regularize nonparametric learners

Uses Software

• Torch
• TensorFlow

Cites Work

• Unnamed Item
• The dropout learning algorithm
• Population theory for boosting ensembles.
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Random classification noise defeats all convex potential boosters
• On the Inductive Bias of Dropout
• Convexity, Classification, and Risk Bounds

This page was built for publication: Surprising properties of dropout in deep networks