# Yoshua Bengio - Universite de Montreal

## Contact Details

NameYoshua Bengio |
||

AffiliationUniversite de Montreal |
||

CityMontréal |
||

CountryCanada |
||

## Pubs By Year |
||

## Pub CategoriesComputer Science - Learning (38) Computer Science - Neural and Evolutionary Computing (20) Statistics - Machine Learning (14) Computer Science - Computation and Language (13) Computer Science - Computer Vision and Pattern Recognition (11) Computer Science - Artificial Intelligence (4) Computer Science - Sound (2) Computer Science - Mathematical Software (1) Quantitative Biology - Neurons and Cognition (1) Computer Science - Symbolic Computation (1) |

## Publications Authored By Yoshua Bengio

In this paper we propose a novel model for unconditional audio generation based on generating one audio sample at a time. We show that our model, which profits from combining memory-less modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure is able to capture underlying sources of variations in the temporal sequences over very long time spans, on three datasets of different nature. Human evaluation on the generated samples indicate that our model is preferred over competing models. Read More

Recent work in the literature has shown experimentally that one can use the lower layers of a trained convolutional neural network (CNN) to model natural textures. More interestingly, it has also been experimentally shown that only one layer with random filters can also model textures although with less variability. In this paper we ask the question as to why one layer CNNs with random filters are so effective in generating textures? We theoretically show that one layer convolutional architectures (without a non-linearity) paired with the an energy function used in previous literature, can in fact preserve and modulate frequency coefficients in a manner so that random weights and pretrained weights will generate the same type of images. Read More

Humans learn a predictive model of the world and use this model to reason about future events and the consequences of actions. In contrast to most machine predictors, we exhibit an impressive ability to generalize to unseen scenarios and reason intelligently in these settings. One important aspect of this ability is physical intuition(Lake et al. Read More

Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very particular functional shape of the trained discriminators in high dimensional spaces, which can easily make training stuck or push probability mass in the wrong direction, towards that of higher concentration than that of the data generating distribution. We introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN models. Read More

Generating high-resolution, photo-realistic images has been a long-standing goal in machine learning. Recently, Nguyen et al. (2016) showed one interesting way to synthesize novel images by performing gradient ascent in the latent space of a generator network to maximize the activations of one or multiple neurons in a separate classifier network. Read More

State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Read More

Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Read More

Modern automatic speech recognition (ASR) systems need to be robust under acoustic variability arising from environmental, speaker, channel, and recording conditions. Ensuring such robustness to variability is a challenge in modern day neural network-based ASR systems, especially when all types of variability are not seen during training. We attempt to address this problem by encouraging the neural network acoustic model to learn invariant feature representations. Read More

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the computations performed with these models especially when considering development of specialized low-power hardware for deep networks. One way of reducing the computational needs is to limit the numerical precision of the network weights and biases, and this will be addressed for the case of RNNs. Read More

The Teacher Forcing algorithm trains recurrent networks by supplying observed sequence values as inputs during training and using the network's own one-step-ahead predictions to do multi-step sampling. We introduce the Professor Forcing algorithm, which uses adversarial domain adaptation to encourage the dynamics of the recurrent network to be the same when training the network and when sampling from the network over multiple time steps. We apply Professor Forcing to language modeling, vocal synthesis on raw waveforms, handwriting generation, and image generation. Read More

Neural network models have a reputation for being black boxes. We propose a new method to understand better the roles and dynamics of the intermediate layers. This has direct consequences on the design of such models and it enables the expert to be able to justify certain heuristics (such as the auxiliary heads in the Inception model). Read More

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. Read More

Learning both hierarchical and temporal representation has been among the long-standing challenges of recurrent neural networks. Multiscale recurrent neural networks have been considered as a promising approach to resolve this issue, yet there has been a lack of empirical evidence showing that this type of models can actually capture the temporal dependencies by discovering the latent hierarchical structure of the sequence. In this paper, we propose a novel multiscale approach, called the hierarchical multiscale recurrent neural networks, which can capture the latent hierarchical structure in the sequence by encoding the temporal dependencies with different timescales using a novel update mechanism. Read More

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the computations performed with these models especially when considering development of specialized low-power hardware for deep networks. One way of reducing the computational needs is to limit the numerical precision of the network weights and biases. Read More

The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss function, e.g. it can involve pathological landscapes such as saddle-surfaces that can be difficult to escape for algorithms based on simple gradient descent. Read More

Communicating knowledge is a primary purpose of language. However, current language models have significant limitations in their ability to encode or decode knowledge. This is mainly because they acquire knowledge based on statistical co-occurrences, even if most of the knowledge words are rarely observed named entities. Read More

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models must generate tokens conditioned on their previous guesses rather than the ground-truth tokens. We address this problem by introducing a \textit{critic} network that is trained to predict the value of an output token, given the policy of an \textit{actor} network. Read More

We introduce a deep learning image segmentation framework that is extremely robust to missing imaging modalities. Instead of attempting to impute or synthesize missing data, the proposed approach learns, for each modality, an embedding of the input image into a single latent vector space for which arithmetic operations (such as taking the mean) are well defined. Points in that space, which are averaged over modalities available at inference time, can then be further processed to yield the desired segmentation. Read More

We first observe a potential weakness of continuous vector representations of symbols in neural machine translation. That is, the continuous vector representation, or a word embedding vector, of a symbol encodes multiple dimensions of similarity, equivalent to encoding more than one meaning of the word. This has the consequence that the encoder and decoder recurrent networks in neural machine translation need to spend substantial amount of their capacity in disambiguating source and target words based on the context which is defined by a source sentence. Read More

In this paper, we extend neural Turing machine (NTM) into a dynamic neural Turing machine (D-NTM) by introducing a trainable memory addressing scheme. This scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing strategies including both linear and nonlinear ones. Read More

Recent deep learning based approaches have achieved great success on handwriting recognition. Chinese characters are among the most widely adopted writing systems in the world. Previous research has mainly focused on recognizing handwritten Chinese characters. Read More

We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs). MI changes the way in which information from difference sources flows and is integrated in the computational building block of an RNN, while introducing almost no extra parameters. The new structure can be easily embedded into many popular RNN models, including LSTMs and GRUs. Read More

Recent deep learning based methods have achieved the state-of-the-art performance for handwritten Chinese character recognition (HCCR) by learning discriminative representations directly from raw data. Nevertheless, we believe that the long-and-well investigated domain-specific knowledge should still help to boost the performance of HCCR. By integrating the traditional normalization-cooperated direction-decomposed feature map (directMap) with the deep convolutional neural network (convNet), we are able to obtain new highest accuracies for both online and offline HCCR on the ICDAR-2013 competition database. Read More

Training energy-based probabilistic models is confronted with apparently intractable sums, whose Monte Carlo estimation requires sampling from the estimated probability distribution in the inner loop of training. This can be approximately achieved by Markov chain Monte Carlo methods, but may still face a formidable obstacle that is the difficulty of mixing between modes with sharp concentrations of probability. Whereas an MCMC process is usually derived from a given energy function based on mathematical considerations and requires an arbitrarily long time to obtain good and varied samples, we propose to train a deep directed generative model (not a Markov chain) so that its sampling distribution approximately matches the energy function that is being trained. Read More

We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document. Unlike previous models, we do not collapse the query into a single vector, instead we deploy an iterative alternating attention mechanism that allows a fine-grained exploration of both the query and the document. Our model outperforms state-of-the-art baselines in standard machine comprehension benchmarks such as CNN news articles and the Children's Book Test (CBT) dataset. Read More

We consider deep multi-layered generative models such as Boltzmann machines or Hopfield nets in which computation (which implements inference) is both recurrent and stochastic, but where the recurrence is not to model sequential structure, only to perform computation. We find conditions under which a simple feedforward computation is a very good initialization for inference, after the input units are clamped to observed values. It means that after the feedforward initialization, the recurrent network is very close to a fixed point of the network dynamics, where the energy gradient is 0. Read More

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ensemble, improving generalization. Read More

We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens. There are many ways to estimate or learn the high-level coarse tokens, but we argue that a simple extraction procedure is sufficient to capture a wealth of high-level discourse semantics. Such procedure allows training the multiresolution recurrent neural network by maximizing the exact joint log-likelihood over both sequences. Read More

Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which require the network to read from extremely large memories. Read More

Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue. In an effort to model this kind of generative process, we propose a neural network-based generative architecture, with latent stochastic variables that span a variable number of time steps. We apply the proposed model to the task of dialogue response generation and compare it with recent neural network architectures. Read More

**Authors:**The Theano Development Team, Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre-Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Mélanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian Goodfellow, Matt Graham, Caglar Gulcehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrancois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert T. McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang

Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively and continuously developed since 2008, multiple frameworks have been built on top of it and it has been used to produce many state-of-the-art machine learning models. Read More

The problem of rare and unknown words is an important issue that can potentially influence the performance of many NLP systems, including both the traditional count-based and the deep learning models. We propose a novel way to deal with the rare and unseen words for the neural network models using attention. Our model uses two softmax layers in order to predict the next word in conditional language models: one predicts the location of a word in the source sentence, and the other predicts a word in the shortlist vocabulary. Read More

Over the past decade, large-scale supervised learning corpora have enabled machine learning researchers to make substantial advances. However, to this date, there are no large-scale question-answer corpora available. In this paper we present the 30M Factoid Question-Answer Corpus, an enormous question answer pair corpus produced by applying a novel neural network architecture on the knowledge base Freebase to transduce facts into natural language questions. Read More

The existing machine translation systems, whether phrase-based or neural, have relied almost exclusively on word-level modelling with explicit segmentation. In this paper, we ask a fundamental question: can neural machine translation generate a character sequence without any explicit segmentation? To answer this question, we evaluate an attention-based encoder-decoder with a subword-level encoder and a character-level decoder on four language pairs--En-Cs, En-De, En-Ru and En-Fi-- using the parallel corpora from WMT'15. Our experiments show that the models with a character-level decoder outperform the ones with a subword-level decoder on all of the four language pairs. Read More

Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only). Gating mechanisms that use softly saturating activation functions to emulate the discrete switching of digital logic circuits are good examples of this. We propose to exploit the injection of appropriate noise so that the gradients may flow easily, even if the noiseless application of the activation function would yield zero gradient. Read More

In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs). Our main contribution is twofold: first, we present a rigorous graph-theoretic framework describing the connecting architectures of RNNs in general. Second, we propose three architecture complexity measures of RNNs: (a) the recurrent depth, which captures the RNN's over-time nonlinear complexity, (b) the feedforward depth, which captures the local input-output nonlinearity (similar to the "depth" in feedforward neural networks (FNNs)), and (c) the recurrent skip coefficient which captures how rapidly the information propagates over time. Read More

We introduce Equilibrium Propagation (e-prop), a learning algorithm for energy-based models. This algorithm involves only one kind of neural computation both for the first phase (when the prediction is made) and the second phase (after the target is revealed) of training. Contrary to backpropagation in feedforward networks, there is no need for special computation in the second phase of our learning algorithm. Read More

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During the forward pass, BNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations, which is expected to substantially improve power-efficiency. Read More

We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is shared across all language pairs. Read More

Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injected in their stochastic hidden layer, with a regularizer that encourages this noise injection. In this paper, we show that injecting noise both in input and in the stochastic hidden layer can be advantageous and we propose a modified variational lower bound as an improved objective function in this setup. When input is corrupted, then the standard VAE lower bound involves marginalizing the encoder conditional distribution over the input noise, which makes the training criterion intractable. Read More

The Manual labeling of data is and will remain a costly endeavor. For this reason, semi-supervised learning remains a topic of practical importance. The recently proposed Ladder Network is one such approach that has proven to be very successful. Read More

We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed architecture, called ReSeg, is based on the recently introduced ReNet model for image classification. We modify and extend it to perform the more challenging task of semantic segmentation. Read More

Often, the performance on a supervised machine learning task is evaluated with a emph{task loss} function that cannot be optimized directly. Examples of such loss functions include the classification error, the edit distance and the BLEU score. A common workaround for this problem is to instead optimize a emph{surrogate loss} function, such as for instance cross-entropy or hinge loss. Read More

Recurrent neural networks (RNNs) are notoriously difficult to train. When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and exploding gradients, especially when trying to learn long-term dependencies. To circumvent this problem, we propose a new architecture that learns a unitary weight matrix, with eigenvalues of absolute value exactly 1. Read More

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 distributing deep learning in which one set of workers search for the most informative examples in parallel while a single worker updates the model on examples selected by importance sampling. This leads the model to update using an unbiased estimate of the gradient which also has minimum variance when the sampling proposal is proportional to the L2-norm of the gradient. Read More

The task of associating images and videos with a natural language description has attracted a great amount of attention recently. Rapid progress has been made in terms of both developing novel algorithms and releasing new datasets. Indeed, the state-of-the-art results on some of the standard datasets have been pushed into the regime where it has become more and more difficult to make significant improvements. Read More

Deep Neural Networks (DNN) have achieved state-of-the-art results in a wide range of tasks, with the best results obtained with large training sets and large models. In the past, GPUs enabled these breakthroughs because of their greater computational speed. In the future, faster computation at both training and test time is likely to be crucial for further progress and for consumer applications on low-power devices. Read More

For most deep learning algorithms training is notoriously time consuming. Since most of the computation in training neural networks is typically spent on floating point multiplications, we investigate an approach to training that eliminates the need for most of these. Our method consists of two parts: First we stochastically binarize weights to convert multiplications involved in computing hidden states to sign changes. Read More

We show that Langevin MCMC inference in an energy-based model with latent variables has the property that the early steps of inference, starting from a stationary point, correspond to propagating error gradients into internal layers, similarly to back-propagation. The error that is back-propagated is with respect to visible units that have received an outside driving force pushing them away from the stationary point. Back-propagated error gradients correspond to temporal derivatives of the activation of hidden units. Read More

Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to train and difficult to parallelize. Recent work has shown that normalizing intermediate representations of neural networks can significantly improve convergence rates in feedforward neural networks . Read More