Publications

Option-Critic in Cooperative Multi-Agent Systems
Jhelum Chakravorty
Nadeem Ward
Julien Roy
Maxime Chevalier-Boisvert
Sumana Basu
Andrei Lupu
Doina Precup
In this paper, we investigate learning temporal abstractions in cooperative multi-agent systems, using the options framework (Sutton et al, … (voir plus)1999). First, we address the planning problem for the decentralized POMDP represented by the multi-agent system, by introducing a \emph{common information approach}. We use the notion of \emph{common beliefs} and broadcasting to solve an equivalent centralized POMDP problem. Then, we propose the Distributed Option Critic (DOC) algorithm, which uses centralized option evaluation and decentralized intra-option improvement. We theoretically analyze the asymptotic convergence of DOC and build a new multi-agent environment to demonstrate its validity. Our experiments empirically show that DOC performs competitively against baselines and scales with the number of agents.
2020-05-04
International Joint Conference on Autonomous Agents and Multiagent Systems (publié)
doi.org
arxiv.org
Multi-Task Self-Supervised Learning for Robust Speech Recognition
Mirco Ravanelli
Jianyuan Zhong
Santiago Pascual
Pawel Swietojanski
Joao Monteiro
Jan Trmal
Yoshua Bengio
Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To t… (voir plus)ake a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that combines a convolutional encoder followed by multiple neural networks, called workers, tasked to solve self-supervised problems (i.e., ones that do not require manual annotations as ground truth). PASE was shown to capture relevant speech information, including speaker voice-print and phonemes. This paper proposes PASE+, an improved version of PASE for robust speech recognition in noisy and reverberant environments. To this end, we employ an online speech distortion module, that contaminates the input signals with a variety of random disturbances. We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks. Finally, we refine the set of workers used in self-supervision to encourage better cooperation. Results on TIMIT, DIRHA and CHiME-5 show that PASE+ significantly outperforms both the previous version of PASE as well as common acoustic features. Interestingly, PASE+ learns transferable representations suitable for highly mismatched acoustic conditions.
2020-05-03
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)
doi.org
arxiv.org
Suitable e-Health Solutions for Older Adults with Dementia or Mild Cognitive Impairment: Perceptions of Health and Social Care Providers in Quebec City
Marie-Pierre Gagnon
Mame Ndiaye
Mylène Boucher
Samantha Dequanter
Ronald Buyl
Ellen Gorus
Anne Bourbonnais
Anik Giguère
S. A. Rahimi
: e-Health solutions offer a potential to improve the quality of life and safety of older adults with dementia or mild cognitive impairment … (voir plus)(MCI). In making better decisions for using eHealth technologies, health professionals should be aware and well informed about existing tools. Recent research shows the lack of knowledge on these technologies for older adults with dementia. In Quebec, current market offer for these technologies is supply-based, and not need-based. This study is part of a larger project and aims to understand the perceptions and needs of health and social care providers regarding e-health technologies for older adults with dementia or MCI. One focus group was carried out with six health and social care professionals at the St-Sacrement Hospital in Quebec City, Canada. The focus group enquired about the use of Information and Communication Technology (ICT) with older adults with cognitive impairment. Relevant examples of ICTs were presented to assess their knowledge level. The discussion was tape-recorded and transcripts were coded using the Nvivo software. Results revealed that aside from fall safety technologies, there is a lack of knowledge about other e-Health technologies for this population. Respondents acknowledged the value of ICTs and were willing to recommend some of them. Economic reasons, blind trust on ICTs and lack of confidence in patients’ capacity to use the solutions were the major limitations identified.
2020-05-02
Proceedings of the 6th International Conference on Information and Communication Technologies for Ageing Well and e-Health (publié)
doi.org
Bringing proportional recovery into proportion: Bayesian modelling of post-stroke motor impairment
Anna K Bonkhoff
Thomas Hope
Danilo Bzdok
Adrian G Guggisberg
Rachel L Hawe
Sean P Dukelow
Anne K Rehme
Gereon R Fink
Christian Grefkes
Howard Bowman
Accurate predictions of motor impairment after stroke are of cardinal importance for the patient, clinician, and healthcare system. More tha… (voir plus)n 10 years ago, the proportional recovery rule was introduced by promising that high-fidelity predictions of recovery following stroke were based only on the initially lost motor function, at least for a specific fraction of patients. However, emerging evidence suggests that this recovery rule is subject to various confounds and may apply less universally than previously assumed. Here, we systematically revisited stroke outcome predictions by applying strategies to avoid confounds and fitting hierarchical Bayesian models. We jointly analysed 385 post-stroke trajectories from six separate studies—one of the largest overall datasets of upper limb motor recovery. We addressed confounding ceiling effects by introducing a subset approach and ensured correct model estimation through synthetic data simulations. Subsequently, we used model comparisons to assess the underlying nature of recovery within our empirical recovery data. The first model comparison, relying on the conventional fraction of patients called ‘fitters’, pointed to a combination of proportional to lost function and constant recovery. ‘Proportional to lost’ here describes the original notion of proportionality, indicating greater recovery in case of a more severe initial impairment. This combination explained only 32% of the variance in recovery, which is in stark contrast to previous reports of >80%. When instead analysing the complete spectrum of subjects, ‘fitters’ and ‘non-fitters’, a combination of proportional to spared function and constant recovery was favoured, implying a more significant improvement in case of more preserved function. Explained variance was at 53%. Therefore, our quantitative findings suggest that motor recovery post-stroke may exhibit some characteristics of proportionality. However, the variance explained was substantially reduced compared to what has previously been reported. This finding motivates future research moving beyond solely behaviour scores to explain stroke recovery and establish robust and discriminating single-subject predictions.
2020-04-30
Brain (publié)
doi.org
General Principles of Gene Dosage Effects on Brain Structure
Claudia Modenato
Kuldeep Kumar
Clara A. Moreau
Catherine Schramm
Guillaume Huguet
Sandra Martin-Brevet
Aurélie Pain
Anne M. Maillard
Sonia Richetin
Borja Rodriguez-Herreros
Lester Melie-Garcia
Ana Dos Santos Silva
Marianne B.M. van den Bree
David E.J. Linden
Carrie E. Bearden
Danilo Bzdok
Sarah Lippé
Mallar Chakravarty
Bogdan Draganski
Sébastien Jacquemont
2020-04-30
Biological Psychiatry (publié)
doi.org
HipoRank: Incorporating Hierarchical and Positional Information into Graph-based Unsupervised Long Document Extractive Summarization
Yue Dong
Andrei Mircea
Jackie CK Cheung
We propose a novel graph-based ranking model for unsupervised extractive summarization of long documents. Graph-based ranking models typical… (voir plus)ly represent documents as undirected fully-connected graphs, where a node is a sentence, an edge is weighted based on sentence-pair similarity, and sentence importance is measured via node centrality. Our method leverages positional and hierarchical information grounded in discourse structure to augment a document's graph representation with hierarchy and directionality. Experimental results on PubMed and arXiv datasets show that our approach outperforms strong unsupervised baselines by wide margins and performs comparably to some of the state-of-the-art supervised models that are trained on hundreds of thousands of examples. In addition, we find that our method provides comparable improvements with various distributional sentence representations; including BERT and RoBERTa models fine-tuned on sentence similarity.
2020-04-30
ArXiv (prépublication)
arxiv.org
arxiv.org
Route choice behaviour and travel information in a congested network: Static and dynamic recursive models
G. M. Ramos
Tien Mai
W. Daamen
Emma Frejinger
S. Hoogendoorn
2020-04-30
Transportation Research Part C: Emerging Technologies (publié)
doi.org
What Can Machine Learning Do for Psychiatry?
Daniel S. Barron
Danilo Bzdok
John H. Krystal
R. Todd Constable
2020-04-30
Biological Psychiatry (publié)
doi.org
Autism spectrum heterogeneity: fact or artifact?
Laurent Mottron
Danilo Bzdok
2020-04-29
Molecular Psychiatry (publié)
doi.org
Continual Weight Updates and Convolutional Architectures for Equilibrium Propagation
Maxence Ernoult
Julie Grollier
Damien Querlioz
Yoshua Bengio
Benjamin Scellier
Equilibrium Propagation (EP) is a biologically inspired alternative algorithm to backpropagation (BP) for training neural networks. It appli… (voir plus)es to RNNs fed by a static input x that settle to a steady state, such as Hopfield networks. EP is similar to BP in that in the second phase of training, an error signal propagates backwards in the layers of the network, but contrary to BP, the learning rule of EP is spatially local. Nonetheless, EP suffers from two major limitations. On the one hand, due to its formulation in terms of real-time dynamics, EP entails long simulation times, which limits its applicability to practical tasks. On the other hand, the biological plausibility of EP is limited by the fact that its learning rule is not local in time: the synapse update is performed after the dynamics of the second phase have converged and requires information of the first phase that is no longer available physically. Our work addresses these two issues and aims at widening the spectrum of EP from standard machine learning models to more bio-realistic neural networks. First, we propose a discrete-time formulation of EP which enables to simplify equations, speed up training and extend EP to CNNs. Our CNN model achieves the best performance ever reported on MNIST with EP. Using the same discrete-time formulation, we introduce Continual Equilibrium Propagation (C-EP): the weights of the network are adjusted continually in the second phase of training using local information in space and time. We show that in the limit of slow changes of synaptic strengths and small nudging, C-EP is equivalent to BPTT (Theorem 1). We numerically demonstrate Theorem 1 and C-EP training on MNIST and generalize it to the bio-realistic situation of a neural network with asymmetric connections between neurons.
2020-04-28
ArXiv (prépublication)
arxiv.org
arxiv.org
Equilibrium Propagation with Continual Weight Updates
Maxence Ernoult
Julie Grollier
Damien Querlioz
Yoshua Bengio
Benjamin Scellier
Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching… (voir plus) those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an input
2020-04-28
arXiv (prépublication)
doi.org
openreview.net
CNN to detect differences in cerebral cortical anatomy of left- and right- handers
Lisa Meyer-Baese
Erik Roecher
Lucas Moesch
Danilo Bzdok
Klaus Mathiak
Handedness is one of the most obvious functional asymmetries, but its relation to anatomical asymmetry in the brain has not yet been clearly… (voir plus) demonstrated. However, there is no significant evidence to prove or disprove this structure-function correlation, thus left-handed patients are often excluded from magnetic resonance imaging (MRI) studies. MRI classification of left and right hemispheres is a difficult task on its own due to the complexity of the images and the structural similarities between the two halves. We demonstrate a deep artificial neural network approach in connection with a detailed preprocessing pipeline for the classification of lateralization in T1-weighted MR images of the human brain. Preprocessing includes bias field correction and registration on the MNI template. Our classifier is a convolutional neural network (CNN) that was trained on 287 images. Each image was duplicated and mirrored on the mid-sagittal plane. The best model reached an accuracy of 97.594% with a mean of 95.42% and standard deviation of 1.37%. Additionally, our model’s performance was evaluated on an independent set of 118 images and reached a classification accuracy of 97%. In a larger study we tested the model on grey-matter images of 927 left and 927 right-handed patients from the UK Biobank. Here all right-handed images and all left-handed images were classified as belonging to one class. The results suggest that there is no structural difference in grey-matter between the two hemispheres that can be distinguished by the deep learning classifier.
2020-04-26
Real-Time Image Processing and Deep Learning 2020 (publié)
doi.org