Publications

A Deep Reinforcement Learning Chatbot (Short Version)
Iulian V. Serban
Chinnadhurai Sankar
Mathieu Germain
Saizheng Zhang
Zhouhan Lin
Sandeep Subramanian
Taesup Kim
Michael Pieper
Sarath Chandar
Nan Rosemary Ke
Sai Rajeswar
Alexandre De Brébisson
Jose M. R. Sotelo
Dendi Suhubdy
Vincent Michalski
Alexandre Nguyen
Joelle Pineau
Yoshua Bengio
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon … (voir plus)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.
2018-01-19
arXiv (Cornell University) (prépublication)
doi.org
arxiv.org
A3T: Adversarially Augmented Adversarial Training
Akram Erraqabi
Aristide Baratin
Yoshua Bengio
Simon Lacoste-Julien
Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations o… (voir plus)f the input data purposely designed to fool a machine learning classifier. Most classification models, including deep learning models, are highly vulnerable to adversarial attacks. In this work, we investigate a procedure to improve adversarial robustness of deep neural networks through enforcing representation invariance. The idea is to train the classifier jointly with a discriminator attached to one of its hidden layer and trained to filter the adversarial noise. We perform preliminary experiments to test the viability of the approach and to compare it to other standard adversarial training methods.
2018-01-11
ArXiv (prépublication)
arxiv.org
arxiv.org
Second-Order Raman Scattering in Exfoliated Black Phosphorus
Alexandre Favron
Félix Antoine Goudreault
Vincent Gosselin
Julien Groulx
Michel Côté
Richard Leonelli
Jean-Francis Germain
Anne-Laurence Phaneuf-L’Heureux
Sébastien Francoeur
Richard Martel
Second-order Raman scattering has been extensively studied in carbon-based nanomaterials, for example, nanotube and graphene, because it act… (voir plus)ivates normally forbidden Raman modes that are sensitive to crystal disorder, such as defects, dopants, strain, and so forth. The sp2-hybridized carbon systems are, however, the exception among nanomaterials, where first-order Raman processes usually dominate. Here we report the identification of four second-order Raman modes, named D1, D1′, D2 and D2′, in exfoliated black phosphorus (P(black)), an elemental direct-gap semiconductor exhibiting strong mechanical and electronic anisotropies. Located in close proximity to the Ag1 and Ag2 modes, these new modes dominate at an excitation wavelength of 633 nm. Their evolutions as a function of sample thickness, excitation wavelength, and defect density indicate that they are defect-activated and involve high-momentum phonons in a doubly resonant Raman process. Ab initio simulations of a monolayer reveal that the D′ and D modes occur through intravalley scatterings with split contributions in the armchair and zigzag directions, respectively. The high sensitivity of these D modes to disorder helps explaining several discrepancies found in the literature.
2018-01-10
Nano Letters (publié)
doi.org
arxiv.org
Modular Networks for Validating Community Detection Algorithms
Justin J Fagnan
Afra Abnar
Reihaneh Rabbany
Osmar R Zaiane
How can we accurately compare different community detection algorithms? These algorithms cluster nodes in a given network, and their perform… (voir plus)ance is often validated on benchmark networks with explicit ground-truth communities. Given the lack of cluster labels in real-world networks, a model that generates realistic networks is required for accurate evaluation of these algorithm. In this paper, we present a simple, intuitive, and flexible benchmark generator to generate intrinsically modular networks for community validation. We show how the generated networks closely comply with the characteristics observed for real networks; whereas their characteristics could be directly controlled to match wide range of real world networks. We further show how common community detection algorithms rank differently when being evaluated on these benchmarks compared to current available alternatives.
2018-01-03
ArXiv (prépublication)
arxiv.org
arxiv.org
Advances in Artificial Intelligence
Ebrahim Bagheri
Jackie CK Cheung
2017-12-31
Lecture Notes in Computer Science (publié)
doi.org
Analyzing Alzheimer’s Disease Progression from Sequential Magnetic Resonance Imaging Scans Using Deep 3D Convolutional Neural Networks
Sumana Basu
Konrad Wagstyl
Azar Zandifar
Louis Collins
Adriana Romero
Doina Precup
Alzheimer’s is a progressive, neurodegenerative disease, that causes irreversible damage to the brain tissue. It impairs the ability to fo… (voir plus)rm and retrieve memory, and eventually disrupts the natural flow of life, by affecting the ability to carry out even day to day activities. The disease is typically diagnosed from the symptoms (Mini Mental State Examination, [8]), such as decline in cognitive abilities, visual and/or speech impairment, loss of memory, rather than the structural changes in the brain (biomarker) that causes it. But the pathological changes in the brain start decades before the manifestation of the symptoms [7]. Magnetic Resonance Imaging (MRI) is capable of capturing the complex changes in the brain, even if it is difficult for humans to extract those features from the low contrast, multi-dimensional MRIs [1]. There is a considerable amount of work on analyzing Alzheimer’s disease. However, the vast majority intends to predict the state of the disease at the current time step.
2017-12-31
(publié)
www.semanticscholar.org
Automatic differentiation in ML: Where we are and where we should be going
Bart Van Merriënboer
Olivier Breuleux
Arnaud Bergeron
Pascal Lamblin
We review the current state of automatic differentiation (AD) for array programming in machine learning (ML), including the different approa… (voir plus)ches such as operator overloading (OO) and source transformation (ST) used for AD, graph-based intermediate representations for programs, and source languages. Based on these insights, we introduce a new graph-based intermediate representation (IR) which specifically aims to efficiently support fully-general AD for array programming. Unlike existing dataflow programming representations in ML frameworks, our IR naturally supports function calls, higher-order functions and recursion, making ML models easier to implement. The ability to represent closures allows us to perform AD using ST without a tape, making the resulting derivative (adjoint) program amenable to ahead-of-time optimization using tools from functional language compilers, and enabling higher-order derivatives. Lastly, we introduce a proof of concept compiler toolchain called Myia which uses a subset of Python as a front end.
Bayesian Model-Agnostic Meta-Learning
Taesup Kim
Jaesik Yoon
Ousmane Dia
Sungwoong Kim
Yoshua Bengio
Sungjin Ahn
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty … (voir plus)inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines scalable gradient-based meta-learning with nonparametric variational inference in a principled probabilistic framework. During fast adaptation, the method is capable of learning complex uncertainty structure beyond a point estimate or a simple Gaussian approximation. In addition, a robust Bayesian meta-update mechanism with a new meta-loss prevents overfitting during meta-update. Remaining an efficient gradient-based meta-learner, the method is also model-agnostic and simple to implement. Experiment results show the accuracy and robustness of the proposed method in various tasks: sinusoidal regression, image classification, active learning, and reinforcement learning.
2017-12-31
Advances in Neural Information Processing Systems 31 (NeurIPS 2018) (publié)
arxiv.org
arxiv.org
BigBrain: 1D convolutional neural networks for automated sementation of cortical layers
Konrad Wagstyl
Claude Lepage
Karl Zilles
Sebastian Bludau
G. Cucurul
Alan C. Evans
Paul C Fletcher
Adriana Romero
Joseph Paul Cohen
Stéphanie Larocque
Thomas Funck
Katrin Amunts
Yoshua Bengio
2017-12-31
(publié)
www.semanticscholar.org
Challenging Conventional Segmentation Evaluation Metrics Focal Pathology ( Lesion and Tumour ) Segmentation from Patient Images
Tal Arbel
2017-12-31
(publié)
www.semanticscholar.org
Commonsense mining as knowledge base completion? A study on the impact of novelty
Stanisław Jastrzębski
Dzmitry Bahdanau
Seyedarian Hosseini
Michael Noukhovitch
Yoshua Bengio
Jackie Chi Kit Cheung
Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples. Inspired by the recent work by Li et a… (voir plus)l., we analyse if knowledge base completion models can be used to mine commonsense knowledge from raw text. We propose novelty of predicted triples with respect to the training set as an important factor in interpreting results. We critically analyse the difficulty of mining novel commonsense knowledge, and show that a simple baseline method outperforms the previous state of the art on predicting more novel.
2017-12-31
OpenAlex (publié)
doi.org
arxiv.org
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
Yoshua Bengio
In order to understand the organization of the cerebral cortex, it is necessary to create a map or parcellation of cortical areas. Reconstru… (voir plus)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 (présentation orale)
openreview.net
openreview.net