Publications

Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders
Baihan Lin
Guillermo Cecchi
Djallel Bouneffouf
Jenna Reinen
Irina Rish
Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement … (see more)learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain. For the AI community, the development of agents that react differently to different types of rewards can enable us to understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems. Empirically, the proposed model outperforms Q-Learning and Double Q-Learning in artificial scenarios with certain reward distributions and real-world human decision making gambling tasks. Moreover, from the behavioral modeling perspective, our parametric framework can be viewed as a first step towards a unifying computational model capturing reward processing abnormalities across multiple mental conditions and user preferences in long-term recommendation systems.
2019-10-01
NeurIPS.cc/2019/Workshop/Neuro_AI (poster)
openreview.net
openreview.net
Augmenting learning using symmetry in a biologically-inspired domain
Shruti Mishra
Abbas Abdolmaleki
Arthur Guez
Piotr Trochim
Doina Precup
Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the … (see more)natural sciences to reduce the dimensionality of systems of equations. In supervised learning, such as in image classification tasks, rotation, translation and scale invariances are used to augment training datasets. In this work, we use data augmentation in a similar way, exploiting symmetry in the quadruped domain of the DeepMind control suite (Tassa et al. 2018) to add to the trajectories experienced by the actor in the actor-critic algorithm of Abdolmaleki et al. (2018). In a data-limited regime, the agent using a set of experiences augmented through symmetry is able to learn faster. Our approach can be used to inject knowledge of invariances in the domain and task to augment learning in robots, and more generally, to speed up learning in realistic robotics applications.
2019-09-30
ArXiv (preprint)
arxiv.org
arxiv.org
Depth with Nonlinearity Creates No Bad Local Minima in ResNets
Kenji Kawaguchi
Yoshua Bengio
2019-09-30
Neural Networks (published)
doi.org
arxiv.org
Evaluation of a web-based tool for labelling potential hospital outbreaks: a mixed methods study
B. Leclère
David L Buckeridge
D. Lepelletier
2019-09-30
Journal of Hospital Infection (published)
doi.org
Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization
Md Mahfuzur Rahman Siddiquee
Zongwei Zhou
Nima Tajbakhsh
Ruibin Feng
Michael B. Gotway
Yoshua Bengio
Jianming Liang
Generative adversarial networks (GANs) have ushered in a revolution in image-to-image translation. The development and proliferation of GANs… (see more) raises an interesting question: can we train a GAN to remove an object, if present, from an image while otherwise preserving the image? Specifically, can a GAN "virtually heal" anyone by turning his medical image, with an unknown health status (diseased or healthy), into a healthy one, so that diseased regions could be revealed by subtracting those two images? Such a task requires a GAN to identify a minimal subset of target pixels for domain translation, an ability that we call fixed-point translation, which no GAN is equipped with yet. Therefore, we propose a new GAN, called Fixed-Point GAN, trained by (1) supervising same-domain translation through a conditional identity loss, and (2) regularizing cross-domain translation through revised adversarial, domain classification, and cycle consistency loss. Based on fixed-point translation, we further derive a novel framework for disease detection and localization using only image-level annotation. Qualitative and quantitative evaluations demonstrate that the proposed method outperforms the state of the art in multi-domain image-to-image translation and that it surpasses predominant weakly-supervised localization methods in both disease detection and localization. Implementation is available at https://github.com/jlianglab/Fixed-Point-GAN.
2019-09-30
2019 IEEE/CVF International Conference on Computer Vision (ICCV) (published)
doi.org
arxiv.org
Patterns of autism symptoms: hidden structure in the ADOS and ADI-R instruments
Jeremy Lefort-Besnard
Kai Vogeley
Leonhard Schilbach
Gael Varoquaux
Bertrand Thirion
Guillaume Dumas
Danilo Bzdok
2019-09-26
Translational Psychiatry (published)
doi.org
Assessing Generalization in TD methods for Deep Reinforcement Learning
Emmanuel Bengio
Doina Precup
Joelle Pineau
2019-09-24
(published)
openreview.net
openreview.net
{COMPANYNAME}11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery
Shawn Tan
Guillaume Androz
Ahmad Chamseddine
Pierre Fecteau
Aaron Courville
Yoshua Bengio
Joseph Paul Cohen
2019-09-24
(published)
openreview.net
openreview.net
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… (see more) those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an input
2019-09-24
ArXiv (preprint)
openreview.net
openreview.net
Equivariant Entity-Relationship Networks
Devon Graham
Siamak Ravanbakhsh
The relational model is a ubiquitous representation of big-data, in part due to its extensive use in databases. In this paper, we propose th… (see more)e Equivariant Entity-Relationship Network (EERN), which is a Multilayer Perceptron equivariant to the symmetry transformations of the Entity-Relationship model. To this end, we identify the most expressive family of linear maps that are exactly equivariant to entity relationship symmetries, and further show that they subsume recently introduced equivariant maps for sets, exchangeable tensors, and graphs. The proposed feed-forward layer has linear complexity in the data and can be used for both inductive and transductive reasoning about relational databases, including database embedding, and the prediction of missing records. This provides a principled theoretical foundation for the application of deep learning to one of the most abundant forms of data. Empirically, EERN outperforms different variants of coupled matrix tensor factorization in both synthetic and real-data experiments.
2019-09-24
(published)
openreview.net
openreview.net
HighRes-net: Multi-Frame Super-Resolution by Recursive Fusion
Michel Deudon
Alfredo Kalaitzis
Md Rifat Arefin
Israel Goytom
Zhichao Lin
Kris Sankaran
Vincent Michalski
S Ebrahimi Kahou
Julien Cornebise
Yoshua Bengio
2019-09-24
(published)
openreview.net
openreview.net
Learning Neural Causal Models from Unknown Interventions
Nan Rosemary Ke
Olexa Bilaniuk
Anirudh Goyal
Stefan Bauer
Hugo Larochelle
Christopher Pal
Yoshua Bengio
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from obs… (see more)ervational data. However, there are theoretical limitations on the identifiability of underlying structures obtained from observational data alone. Interventional data provides much richer information about the underlying data-generating process. However, the extension and application of methods designed for observational data to include interventions is not straightforward and remains an open problem. In this paper we provide a general framework based on continuous optimization and neural networks to create models for the combination of observational and interventional data. The proposed method is even applicable in the challenging and realistic case that the identity of the intervened upon variable is unknown. We examine the proposed method in the setting of graph recovery both de novo and from a partially-known edge set. We establish strong benchmark results on several structure learning tasks, including structure recovery of both synthetic graphs as well as standard graphs from the Bayesian Network Repository.
2019-09-24
ArXiv (preprint)
openreview.net
openreview.net