Big Neural Networks Waste Capacity Big Neural Networks Waste Capacity
Paper summary This papers show the effects of under-fitting in a neural network as the size of a single neural network layer increases. The overall model is composed of SIFT extraction, k-mean, and this single hidden layer neural network. The paper suggest that this under-fitting problem is due to optimization problems with stochastic gradient descent.
Big Neural Networks Waste Capacity
Dauphin, Yann and Bengio, Yoshua
arXiv e-Print archive - 2013 via Local Bibsonomy
Keywords: dblp

Summary by Martin Thoma 1 year ago
Your comment:
Summary by Open Review 2 years ago
Your comment: allows researchers to publish paper summaries that are voted on and ranked!

Sponsored by: and