Conference item icon

Conference item

Predicting Parameters in Deep Learning

Abstract:

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...

Expand abstract

Actions


Access Document


Files:

Authors


Misha Denil More by this author
Babak Shakibi More by this author
Laurent Dinh More by this author
Marc'Aurelio Ranzato More by this author
Nando de Freitas More by this author
Publication date:
2013
URN:
uuid:24eb6b3a-d833-4f13-93fb-12277843891b
Local pid:
cs:7203

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP