activity
20102013
most citedOn the difficulty of training Recurrent Neural Networks

3.8k citations · 4.9k across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG201319 cited

Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines

Guillaume Desjardins, Razvan Pascanu, Aaron Courville +1

This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm for training Boltzmann Machines. Similar in spirit to the Hessian-Free method of Martens [8], our algorithm…

cs.LG201210 cited

Advances in Optimizing Recurrent Networks

Yoshua Bengio, Nicolas Boulanger-Lewandowski, Razvan Pascanu

After a more than decade-long period of relatively little research activity in the area of recurrent neural networks, several new developments will be reviewed here that have allow…

cs.SC20121k cited

Theano: new features and speed improvements

Frédéric Bastien, Pascal Lamblin, Razvan Pascanu +6

Theano is a linear algebra compiler that optimizes a user's symbolically-specified mathematical computations to produce efficient low-level implementations. In this paper, we prese…

cs.LG20123.8k cited

On the difficulty of training Recurrent Neural Networks

Razvan Pascanu, Tomas Mikolov, Yoshua Bengio

There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this pape…

cs.LG201013 cited

Deep Self-Taught Learning for Handwritten Character Recognition

Frédéric Bastien, Yoshua Bengio, Arnaud Bergeron +14

Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtained…