%0 Journal Article
%T Do Deep Nets Really Need to be Deep?
%A Lei Jimmy Ba
%A Rich Caruana
%J Computer Science
%D 2013
%I arXiv
%X Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision. In this extended abstract, we show that shallow feed-forward networks can learn the complex functions previously learned by deep nets and achieve accuracies previously only achievable with deep models. Moreover, in some cases the shallow neural nets can learn these deep functions using a total number of parameters similar to the original deep model. We evaluate our method on the TIMIT phoneme recognition task and are able to train shallow fully-connected nets that perform similarly to complex, well-engineered, deep convolutional architectures. Our success in training shallow neural nets to mimic deeper models suggests that there probably exist better algorithms for training shallow feed-forward nets than those currently available.
%U http://arxiv.org/abs/1312.6184v7