309 citations · 896 across the 12 of their papers we have counts for
3 papers · 1 filter
Understanding intermediate layers using linear classifier probes
Guillaume Alain, Yoshua Bengio
Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how suitable they are for classification. We…
Variance Reduction in SGD by Distributed Importance Sampling
Guillaume Alain, Alex Lamb, Chinnadhurai Sankar +2
Humans are able to accelerate their learning by selecting training materials that are the most informative and at the appropriate level of difficulty. We propose a framework for di…
Techniques for Learning Binary Stochastic Feedforward Neural Networks
Tapani Raiko, Mathias Berglund, Guillaume Alain +1
Stochastic binary hidden units in a multi-layer perceptron (MLP) network give at least three potential benefits when compared to deterministic MLP networks. (1) They allow to learn…