Authors
Ian J Goodfellow, Oriol Vinyals, Andrew M Saxe
Publication date
2014/12/19
Journal
arXiv preprint arXiv:1412.6544
Description
Abstract: Training neural networks involves solving large-scale non-convex optimization
problems. This task has long been believed to be extremely difficult, with fear of local minima
and other obstacles motivating a variety of schemes to improve optimization, such as
unsupervised pretraining. However, modern neural networks are able to achieve negligible
training error on complex tasks, using only direct training with stochastic gradient descent.
We introduce a simple analysis technique to look for evidence that such networks are ...
Total citations
20152016210
Scholar articles
IJ Goodfellow, O Vinyals, AM Saxe - arXiv preprint arXiv:1412.6544, 2014