GENERAL ENQUIRIES: Tel: + 27 12 841 2911 | Email:

Show simple item record Pretorius, Arnu Kroon, Steve Kamper, Herman 2019-03-07T09:46:57Z 2019-03-07T09:46:57Z 2018-07
dc.identifier.citation Pretorius, A., Kroon, S. and Kamper, H. 2018. Learning dynamics of linear denoising autoencoders. ICML 2018: The 35th International Conference on Machine Learning, Stockholm, Sweden, 10-15 Jul 2018, pp. 4141-4150 en_US
dc.description Copyright 2018 The author(s). en_US
dc.description.abstract Denoising autoencoders (DAEs) have proven useful for unsupervised representation learning, but a thorough theoretical understanding is still lacking of how the input noise influences learning. Here we develop theory for how noise influences learning in DAEs. By focusing on linear DAEs, we are able to derive analytic expressions that exactly describe their learning dynamics. We verify our theoretical predictions with simulations as well as experiments on MNIST and CIFAR-10. The theory illustrates how, when tuned correctly, noise allows DAEs to ignore low variance directions in the inputs while learning to reconstruct them. Furthermore, in a comparison of the learning dynamics of DAEs to standard regularised autoencoders, we show that noise has a similar regularisation effect to weight decay, but with faster training dynamics. We also show that our theoretical predictions approximate learning dynamics on real-world data and qualitatively match observed dynamics in nonlinear DAEs. en_US
dc.language.iso en en_US
dc.relation.ispartofseries Worklist;22132
dc.subject Denoising autoencoders en_US
dc.subject DAEs en_US
dc.subject Learning dynamics en_US
dc.subject Linear DAEs en_US
dc.title Learning dynamics of linear denoising autoencoders en_US
dc.type Presentation en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search ResearchSpace

Advanced Search


My Account