Publications

SigTran: Signature Vectors for Detecting Illicit Activities in Blockchain Transaction Networks
Farimah Poursafaei
Reihaneh Rabbany
Željko Žilić
2021-05-08
Advances in Knowledge Discovery and Data Mining (published)
doi.org
Facilitating Asynchronous Participatory Design of Open Source Software: Bringing End Users into the Loop
Jazlyn Hellman
Jinghui Cheng
Jin L.C. Guo
2021-05-07
Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems (published)
doi.org
arxiv.org
Interprofessional collaboration and health policy: results from a Quebec mixed method legal research
Marie-Andree Girard
Catherine Régis
Jean-Louis Denis
2021-05-05
Journal of Interprofessional Care (published)
doi.org
Pharmacists' perceptions of a machine learning model for the identification of atypical medication orders
Sophie-Camille Hogue
Flora Chen
Geneviève Brassard
Denis Lebel
Jean-François Bussières
Audrey Durand
Maxime Thibault
2021-05-05
J. Am. Medical Informatics Assoc. (published)
doi.org
Impact of individual rater style on deep learning uncertainty in medical imaging segmentation
Olivier Vincent
Charley Gros
Julien Cohen-Adad
While multiple studies have explored the relation between inter-rater variability and deep learning model uncertainty in medical segmentatio… (see more)n tasks, little is known about the impact of individual rater style. This study quantifies rater style in the form of bias and consistency and explores their impacts when used to train deep learning models. Two multi-rater public datasets were used, consisting of brain multiple sclerosis lesion and spinal cord grey matter segmentation. On both datasets, results show a correlation (
2021-05-04
ArXiv (preprint)
arxiv.org
arxiv.org
PNS-GAN: Conditional Generation of Peripheral Nerve Signals in the Wavelet Domain via Adversarial Networks
Olivier Tessier-Larivière
Luke Y. Prince
Pascal Fortier-Poisson
Lorenz Wernisch
Oliver Armitage
Emil Hewage
Guillaume Lajoie
Blake Aaron Richards
Simulated datasets of neural recordings are a crucial tool in neural engineering for testing the ability of decoding algorithms to recover k… (see more)nown ground-truth. In this work, we introduce PNS-GAN, a generative adversarial network capable of producing realistic nerve recordings conditioned on physiological biomarkers. PNS-GAN operates in the wavelet domain to preserve both the timing and frequency of neural events with high resolution. PNS-GAN generates sequences of scaleograms from noise using a recurrent neural network and 2D transposed convolution layers. PNS-GAN discriminates over stacks of scaleograms with a network of 3D convolution layers. We find that our generated signal reproduces a number of characteristics of the real signal, including similarity in a canonical time-series feature-space, and contains physiologically related neural events including respiration modulation and similar distributions of afferent and efferent signalling.
2021-05-03
IEEE/EMBS Conference on Neural Engineering (published)
doi.org
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Ossama Ahmed
Frederik Träuble
Anirudh Goyal
Alexander Neitz
Manuel Wuthrich
Yoshua Bengio
Bernhard Schölkopf
Stefan Bauer
Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environment… (see more)s. To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment. The environment is a simulation of an open-source robotic platform, hence offering the possibility of sim-to-real transfer. Tasks consist of constructing 3D shapes from a given set of blocks - inspired by how children learn to build complex structures. The key strength of CausalWorld is that it provides a combinatorial family of such tasks with common causal structure and underlying factors (including, e.g., robot and object masses, colors, sizes). The user (or the agent) may intervene on all causal variables, which allows for fine-grained control over how similar different tasks (or task distributions) are. One can thus easily define training and evaluation distributions of a desired difficulty level, targeting a specific form of generalization (e.g., only changes in appearance or object mass). Further, this common parametrization facilitates defining curricula by interpolating between an initial and a target task. While users may define their own task distributions, we present eight meaningful distributions as concrete benchmarks, ranging from simple to very challenging, all of which require long-horizon planning as well as precise low-level motor control. Finally, we provide baseline results for a subset of these tasks on distinct training curricula and corresponding evaluation protocols, verifying the feasibility of the tasks in this benchmark.
2021-05-02
International Conference on Learning Representations (Poster)
doi.org
openreview.net
Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
Chin-wei Huang
Ricky T. Q. Chen
Christos Tsirigotis
Aaron Courville
Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows… (see more) (CP-Flow), a natural and efficient parameterization of invertible models inspired by the optimal transport (OT) theory. CP-Flows are the gradient map of a strongly convex neural potential function. The convexity implies invertibility and allows us to resort to convex optimization to solve the convex conjugate for efficient inversion. To enable maximum likelihood training, we derive a new gradient estimator of the log-determinant of the Jacobian, which involves solving an inverse-Hessian vector product using the conjugate gradient method. The gradient estimator has constant-memory cost, and can be made effectively unbiased by reducing the error tolerance level of the convex optimization routine. Theoretically, we prove that CP-Flows are universal density approximators and are optimal in the OT sense. Our empirical results show that CP-Flow performs competitively on standard benchmarks of density estimation and variational inference.
2021-05-02
International Conference on Learning Representations (Poster)
doi.org
openreview.net
Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments
Anirudh Goyal
Alex Lamb
Phanideep Gampa
Philippe Beaudoin
Charles Blundell
Sergey Levine
Yoshua Bengio
Michael Mozer
2021-05-02
International Conference on Learning Representations (Poster)
openreview.net
openreview.net
Integrating Categorical Semantics into Unsupervised Domain Translation
Samuel Lavoie
Faruk Ahmed
Aaron Courville
While unsupervised domain translation (UDT) has seen a lot of success recently, we argue that mediating its translation via categorical sema… (see more)ntic features could broaden its applicability. In particular, we demonstrate that categorical semantics improves the translation between perceptually different domains sharing multiple object categories. We propose a method to learn, in an unsupervised manner, categorical semantic features (such as object labels) that are invariant of the source and target domains. We show that conditioning the style encoder of unsupervised domain translation methods on the learned categorical semantics leads to a translation preserving the digits on MNIST
2021-05-02
International Conference on Learning Representations (Poster)
doi.org
openreview.net
Iterated Learning for Emergent Systematicity in VQA
Ankit Vani
Max Schwarzer
Yuchen Lu
Eeshan Dhekane
Aaron Courville
Although neural module networks have an architectural bias towards compositionality, they require gold standard layouts to generalize system… (see more)atically in practice. When instead learning layouts and modules jointly, compositionality does not arise automatically and an explicit pressure is necessary for the emergence of layouts exhibiting the right structure. We propose to address this problem using iterated learning, a cognitive science theory of the emergence of compositional languages in nature that has primarily been applied to simple referential games in machine learning. Considering the layouts of module networks as samples from an emergent language, we use iterated learning to encourage the development of structure within this language. We show that the resulting layouts support systematic generalization in neural agents solving the more complex task of visual question-answering. Our regularized iterated learning method can outperform baselines without iterated learning on SHAPES-SyGeT (SHAPES Systematic Generalization Test), a new split of the SHAPES dataset we introduce to evaluate systematic generalization, and on CLOSURE, an extension of CLEVR also designed to test systematic generalization. We demonstrate superior performance in recovering ground-truth compositional program structure with limited supervision on both SHAPES-SyGeT and CLEVR.
2021-05-02
International Conference on Learning Representations (Oral)
doi.org
openreview.net
Learning to Live with Dale's Principle: ANNs with Separate Excitatory and Inhibitory Units
Jonathan Cornford
Damjan Kalajdzievski
Marco Leite
Amélie Lamarquette
Dimitri M. Kullmann
Blake Richards
A bstract The units in artificial neural networks (ANNs) can be thought of as abstraction… (see more)s of biological neurons, and ANNs are increasingly used in neuroscience research. However, there are many important differences between ANN units and real neurons. One of the most notable is the absence of Dale’s principle, which ensures that biological neurons are either exclusively excitatory or inhibitory. Dale’s principle is typically left out of ANNs because its inclusion impairs learning. This is problematic, because one of the great advantages of ANNs for neuroscience research is their ability to learn complicated, realistic tasks. Here, by taking inspiration from feedforward inhibitory interneurons in the brain we show that we can develop ANNs with separate populations of excitatory and inhibitory units that learn just as well as standard ANNs. We call these networks Dale’s ANNs (DANNs). We present two insights that enable DANNs to learn well: (1) DANNs are related to normalization schemes, and can be initialized such that the inhibition centres and standardizes the excitatory activity, (2) updates to inhibitory neuron parameters should be scaled using corrections based on the Fisher Information matrix. These results demonstrate how ANNs that respect Dale’s principle can be built without sacrificing learning performance, which is important for future work using ANNs as models of the brain. The results may also have interesting implications for how inhibitory plasticity in the real brain operates.
2021-05-02
ICLR (Poster)
doi.org
openreview.net