On the Inductive Bias of Dropout

zbMath1351.68213arXiv1412.4736MaRDI QIDQ2788414

Philip M. Long, David P. Helmbold

Publication date: 19 February 2016

Full work available at URL: https://arxiv.org/abs/1412.4736

zbMATH Keywords

regularizationlearning theorydropoutinductive biasfeature noising

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items (4)

Dropout training for SVMs with data augmentation ⋮ Dropout fails to regularize nonparametric learners ⋮ Surprising properties of dropout in deep networks ⋮ Adaptive infinite dropout for noisy and sparse data streams

Uses Software

• AdaGrad

This page was built for publication: On the Inductive Bias of Dropout