Predicting Parameters in Deep Learning

06/03/2013
by   Misha Denil, et al.
0

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 accuracy.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset