Yoshua Bengio

Scaling in the Service of Reasoning & Model-Based ML

April 4, 2023

Yoshua Bengio

Edward J. Hu

A collaboration between Mila and Relation Therapeutics to discover novel synergistic combinations of drugs in vitro

March 23, 2022

Paul Bertin

Jake P. Taylor-King

Yoshua Bengio

March 15, 2022

Generative Flow Networks

Yoshua Bengio

Publications

ChatPainter: Improving Text to Image Generation using Dialogue

Shikhar Sharma

Dendi Suhubdy

Vincent Michalski

S Ebrahimi Kahou

Synthesizing realistic images from text descriptions on a dataset like Microsoft Common Objects in Context (MS COCO), where each image can c… (see more)ontain several objects, is a challenging task. Prior work has used text captions to generate images. However, captions might not be informative enough to capture the entire image and insufficient for the model to be able to understand which objects in the images correspond to which words in the captions. We show that adding a dialogue that further describes the scene leads to significant improvement in the inception score and in the quality of generated images on the MS COCO dataset.

2017-12-31

ICLR (Workshop) (published)

Convolutional neural networks for mesh-based parcellation of the cerebral cortex

Guillem Cucurull

Konrad Wagstyl

Arantxa Casanova

Petar Veličković

Estrid Jakobsen

Michal Drozdzal

Adriana Romero

Alan C. Evans

In order to understand the organization of the cerebral cortex, it is necessary to create a map or parcellation of cortical areas. Reconstru… (see more)ctions of the cortical surface created from structural MRI scans, are frequently used in neuroimaging as a common coordinate space for representing multimodal neuroimaging data. These meshes are used to investigate healthy brain organization as well as abnormalities in neurological and psychiatric conditions. We frame cerebral cortex parcellation as a mesh segmentation task, and address it by taking advantage of recent advances in generalizing convolutions to the graph domain. In particular, we propose to assess graph convolutional networks and graph attention networks, which, in contrast to previous mesh parcellation models, exploit the underlying structure of the data to make predictions. We show experimentally on the Human Connectome Project dataset that the proposed graph convolutional models outperform current state-of-the-art and baselines, highlighting the potential and applicability of these methods to tackle neuroimaging challenges, paving the road towards a better characterization of brain diseases.

2017-12-31

MIDL.amsterdam/2018/Conference (oral)

A Dataset of Topic-Oriented Human-to-Chatbot Dialogues

Varvara Logacheva

Mikhail Burtsev

Valentin Malykh

Vadim Poluliakh

Alexander Rudnicky

Iulian V. Serban

Ryan Thomas Lowe

Shrimai Prabhumoye

Alan W. Black

This document contains the description of dataset collected during the first round of Conversational Intelligence Challenge (ConvAI) which t… (see more)ook place in July 2017. During this evaluation round we collected over 2,500 dialogues from 10 chatbots and 500 volunteers. Here we provide the analysis of dataset statistics and outline some possible improvements for future data collection experiments.

2017-12-31

(published)

www.semanticscholar.org

A Deep Reinforcement Learning Chatbot (Short Version)

Iulian V. Serban

Mathieu Germain

Michael Pieper

Nan Rosemary Ke

Sai Rajeswar

Alexandre De Brébisson

Jose M. R. Sotelo

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon … (see more)Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including neural network and template-based models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than other systems. The results highlight the potential of coupling ensemble systems with deep reinforcement learning as a fruitful path for developing real-world, open-domain conversational agents.

2017-12-31

arXiv (preprint)

doi.org

Dendritic cortical microcircuits approximate the backpropagation algorithm

João Sacramento

Rui Ponte Costa

Walter Senn

Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience. However, the main learning mechan… (see more)ism behind these advances - error backpropagation - appears to be at odds with neurobiology. Here, we introduce a multilayer neuronal network model with simplified dendritic compartments in which error-driven synaptic plasticity adapts the network towards a global desired output. In contrast to previous work our model does not require separate phases and synaptic learning is driven by local dendritic prediction errors continuously in time. Such errors originate at apical dendrites and occur due to a mismatch between predictive input from lateral interneurons and activity from actual top-down feedback. Through the use of simple dendritic compartments and different cell-types our model can represent both error and normal activity within a pyramidal neuron. We demonstrate the learning capabilities of the model in regression and classification tasks, and show analytically that it approximates the error backpropagation algorithm. Moreover, our framework is consistent with recent observations of learning between brain areas and the architecture of cortical microcircuits. Overall, we introduce a novel view of learning on dendritic cortical circuits and on how the brain may solve the long-standing synaptic credit assignment problem.

2017-12-31

Advances in Neural Information Processing Systems 31 (NeurIPS 2018) (published)

Disentangling the independently controllable factors of variation by interacting with the world

Valentin Thomas

Philippe Beaudoin

William Fedus

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it rema… (see more)ins an open question what kind of training framework could potentially achieve that. Whereas most previous work focuses on the static setting (e.g., with images), we postulate that some of the causal factors could be discovered if the learner is allowed to interact with its environment. The agent can experiment with different actions and observe their effects. More specifically, we hypothesize that some of these factors correspond to aspects of the environment which are independently controllable, i.e., that there exists a policy and a learnable feature for each such aspect of the environment, such that this policy can yield changes in that feature with minimal changes to other features that explain the statistical variations in the observed data. We propose a specific objective function to find such factors, and verify experimentally that it can indeed disentangle independently controllable aspects of the environment without any extrinsic reward signal.

2017-12-31

arXiv (preprint)

doi.org

FigureQA: An Annotated Figure Dataset for Visual Reasoning

Samira Ebrahimi Kahou

Adam Atkinson

Vincent Michalski

Ákos Kádár

Adam Trischler

We introduce FigureQA, a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images. The images are s… (see more)ynthetic, scientific-style figures from five classes: line plots, dot-line plots, vertical and horizontal bar graphs, and pie charts. We formulate our reasoning task by generating questions from 15 templates; questions concern various relationships between plot elements and examine characteristics like the maximum, the minimum, area-under-the-curve, smoothness, and intersection. To resolve, such questions often require reference to multiple plot elements and synthesis of information distributed spatially throughout a figure. To facilitate the training of machine learning systems, the corpus also includes side data that can be used to formulate auxiliary objectives. In particular, we provide the numerical data used to generate each figure as well as bounding-box annotations for all plot elements. We study the proposed visual reasoning task by training several models, including the recently proposed Relation Network as a strong baseline. Preliminary results indicate that the task poses a significant machine learning challenge. We envision FigureQA as a first step towards developing models that can intuitively recognize patterns from visual representations of data.

2017-12-31

ICLR.cc/2018/Conference (Invite to Workshop Track)

Fraternal Dropout

Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential pred… (see more)iction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A number of techniques have been proposed in literature to address this problem. In this paper we propose a simple technique called fraternal dropout that takes advantage of dropout to achieve this goal. Specifically, we propose to train two identical copies of an RNN (that share parameters) with different dropout masks while minimizing the difference between their (pre-softmax) predictions. In this way our regularization encourages the representations of RNNs to be invariant to dropout mask, thus being robust. We show that our regularization term is upper bounded by the expectation-linear dropout objective which has been shown to address the gap due to the difference between the train and inference phases of dropout. We evaluate our model and achieve state-of-the-art results in sequence modeling tasks on two benchmark datasets - Penn Treebank and Wikitext-2. We also show that our approach leads to performance improvement by a significant margin in image captioning (Microsoft COCO) and semi-supervised (CIFAR-10) tasks.

2017-12-31

ICLR.cc/2018/Conference (poster)

Image-to-image translation for cross-domain disentanglement

Abel Gonzalez-Garcia

Joost van de Weijer

Deep image translation methods have recently shown excellent results, outputting high-quality images covering multiple modes of the data dis… (see more)tribution. There has also been increased interest in disentangling the internal representations learned by deep methods to further improve their performance and achieve a finer control. In this paper, we bridge these two objectives and introduce the concept of cross-domain disentanglement. We aim to separate the internal representation into three parts. The shared part contains information for both domains. The exclusive parts, on the other hand, contain only factors of variation that are particular to each domain. We achieve this through bidirectional image translation based on Generative Adversarial Networks and cross-domain autoencoders, a novel network component. Our model offers multiple advantages. We can output diverse samples covering multiple modes of the distributions of both domains, perform domain-specific image transfer and interpolation, and cross-domain retrieval without the need of labeled data, only paired images. We compare our model to the state-of-the-art in multi-modal image translation and achieve better results for translation on challenging datasets as well as for cross-domain retrieval on realistic datasets.

2017-12-31

NeurIPS (published)

LATTER M INIMA WITH SGD

Stanisław Jastrzębski

Amos Storkey

2017-12-31

(published)

www.semanticscholar.org

Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning

Sandeep Subramanian

Adam Trischler

Christopher Pal

A lot of the recent success in natural language processing (NLP) has been driven by distributed vector representations of words trained on l… (see more)arge amounts of text in an unsupervised manner. These representations are typically used as general purpose features for words across a range of NLP problems. However, extending this success to learning representations of sequences of words, such as sentences, remains an open problem. Recent work has explored unsupervised as well as supervised learning techniques with different training objectives to learn general purpose fixed-length sentence representations. In this work, we present a simple, effective multi-task learning framework for sentence representations that combines the inductive biases of diverse training objectives in a single model. We train this model on several data sources with multiple training objectives on over 100 million sentences. Extensive experiments demonstrate that sharing a single recurrent sentence encoder across weakly related tasks leads to consistent improvements over previous methods. We present substantial improvements in the context of transfer learning and low-resource settings using our learned general-purpose representations.

2017-12-31

ICLR (Poster) (published)

Light Gated Recurrent Units for Speech Recognition

Mirco Ravanaelli

Philemon Brakel

Maurizio Omologo

A field that has directly benefited from the recent advances in deep learning is automatic speech recognition (ASR). Despite the great achie… (see more)vements of the past decades, however, a natural and robust human–machine speech interaction still appears to be out of reach, especially in challenging environments characterized by significant noise and reverberation. To improve robustness, modern speech recognizers often employ acoustic models based on recurrent neural networks (RNNs) that are naturally able to exploit large time contexts and long-term speech modulations. It is thus of great interest to continue the study of proper techniques for improving the effectiveness of RNNs in processing speech signals. In this paper, we revise one of the most popular RNN models, namely, gated recurrent units (GRUs), and propose a simplified architecture that turned out to be very effective for ASR. The contribution of this work is twofold: First, we analyze the role played by the reset gate, showing that a significant redundancy with the update gate occurs. As a result, we propose to remove the former from the GRU design, leading to a more efficient and compact single-gate model. Second, we propose to replace hyperbolic tangent with rectified linear unit activations. This variation couples well with batch normalization and could help the model learn long-term dependencies without numerical issues. Results show that the proposed architecture, called light GRU, not only reduces the per-epoch training time by more than 30% over a standard GRU, but also consistently improves the recognition accuracy across different tasks, input features, noisy conditions, as well as across different ASR paradigms, ranging from standard DNN-HMM speech recognizers to end-to-end connectionist temporal classification models.

2017-12-31

IEEE Trans. Emerg. Top. Comput. Intell. (published)

doi.org