Regularization terms, suchasL2 regularization leading toweightdecay,arecommonly employed during training to improve a model's generalization capabilities.

Made: Maskedautoencoder fordistributionestimation. In Francis Bachand David Blei, editors,Proceedingsofthe 32nd International Conferenceon Machine Learning, volume 37 ofProceedingsof Machine Learning Research, pages 881-889, Lille, France, 07-09 Jul 2015.

Rarely doresearchers attempt tomodel andexamine how individual participants vary from each other - a question that should be addressable even in small samples given the right statistical tools.

A large body of research since the 1980s empirically observed that large neural networks can be compressed orsparsified toasmallfraction oftheiroriginal sizewhilemaintaining theirpredictive accuracy[14-16,20,23,29,45].