Predicting Parameters in Deep Learning

Misha Denil, Babak Shakibi, Laurent Dinh et al. · arXiv (Cornell University) · 2013

We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accurately predict the remaining values. Moreover, we show that not only can the parameter values be predicted, but many of them need not be learned at all. We train several different architectures by learning only a small number of weights and predicting the rest. In the best case we are able to predict more than 95% of the weights of a network without any drop in accuracy.

Cited by 663 works. doi:10.48550/arxiv.1306.0543 Open-access PDF

Authors

References