Yoshua Bengio

TL;DR: This work shows an alternative way to sample from a trained Orderless NADE that allows to trade-off computing time and quality of the samples, and makes a connection between this criterion and the training criterion for Generative Stochastic Networks (GSNs).

TL;DR: In this paper, the authors show that the temporal derivatives of the neural activities in equilibrium propagation are equal to the error derivatives computed iteratively by recurrent backpropagation in the side network.

TL;DR: In this article, the authors put under a common framework a number of non-linear dimensionality reduction methods, such as Locally Linear Embedding, Isomap, Laplacian Eigenmaps and kernel PCA, which are based on performing an eigendecomposition.

TL;DR: This article proposed a two-stage neural model to tackle question generation from documents, which estimates the probability that word sequences in a document are ones that a human would pick when selecting candidate answers by training a neural key-phrase extractor on the answers in a question-answering corpus.

TL;DR: This work extends previous work on score estimation by denoising autoencoders to the case of a conditional distribution, with a novel use of a corrupted feedforward predictor replacing Gaussian corruption and experimentally finds that the proposed iterative inference from conditional Score estimation by conditional denoised autoen coders performs better than comparable models based on CRFs or those not using any explicit modeling of the conditional joint distribution of outputs.