Neural Network Regularization via Robust Weight Factorization
Abstract
Regularization is essential when training large neural networks. As deep neural networks can be mathematically interpreted as universal function approximators, they are effective at memorizing sampling noise in the training data. This results in poor generalization to unseen data. Therefore, it is no surprise that a new regularization technique, Dropout, was partially responsible for the nowubiquitous winning entry to ImageNet 2012 by the University of Toronto. Currently, Dropout (and related methods such as DropConnect) are the most effective means of regularizing large neural networks. These amount to efficiently visiting a large number of related models at training time, while aggregating them to a single predictor at test time. The proposed FaMe model aims to apply a similar strategy, yet learns a factorization of each weight matrix such that the factors are robust to noise.
 Publication:

arXiv eprints
 Pub Date:
 December 2014
 arXiv:
 arXiv:1412.6630
 Bibcode:
 2014arXiv1412.6630R
 Keywords:

 Computer Science  Machine Learning;
 Computer Science  Neural and Evolutionary Computing;
 Statistics  Machine Learning