Publications

INFERNO: Inferring Object-Centric 3D Scene Representations without Supervision
Lluis Castrejon
Nicolas Ballas
Aaron Courville
We propose INFERNO, a method to infer object-centric representations of visual scenes without annotations. Our method decomposes a scene int… (voir plus)o multiple objects, with each object having a structured representation that disentangles its shape, appearance and pose. Each object representation defines a localized neural radiance field used to generate 2D views of the scene through differentiable rendering. Our model is subsequently trained by minimizing a reconstruction loss between inputs and corresponding rendered scenes. We empirically show that INFERNO discovers objects in a scene without supervision. We also validate the interpretability of the learned representations by manipulating inferred scenes and showing the corresponding effect in the rendered output. Finally, we demonstrate the usefulness of our 3D object representations in a visual reasoning task using the CATER dataset.
2022-03-24
ICLR.cc/2022/Workshop/OSC (poster)
openreview.net
openreview.net
Object-centric Compositional Imagination for Visual Abstract Reasoning
Rim Assouel
Pau Rodríguez
Perouz Taslakian
David Vázquez
Yoshua Bengio
Like humans devoid of imagination, current machine learning systems lack the ability to adapt to new, unexpected situations by foreseeing th… (voir plus)em, which makes them unable to solve new tasks by analogical reasoning. In this work, we introduce a new compositional imagination framework that improves a model's ability to generalize. One of the key components of our framework is object-centric inductive biases that enables models to perceive the environment as a series of objects, properties, and transformations. By composing these key ingredients, it is possible to generate new unseen tasks that, when used to train the model, improve generalization. Experiments on a simplified version of the Abstraction and Reasoning Corpus (ARC) demonstrate the effectiveness of our framework.
2022-03-24
ICLR.cc/2022/Workshop/OSC (poster)
openreview.net
openreview.net
Monoallelic Heb/Tcf12 Deletion Reduces the Requirement for NOTCH1 Hyperactivation in T-Cell Acute Lymphoblastic Leukemia
Diogo F. T. Veiga
Mathieu Tremblay
Bastien Gerby
Sabine Herblot
André Haman
Patrick Gendron
Sébastien Lemieux
Juan Carlos Zúñiga-Pflücker
Josée Hébert
Joseph Paul Cohen
Trang Hoang
Early T-cell development is precisely controlled by E proteins, that indistinguishably include HEB/TCF12 and E2A/TCF3 transcription factors,… (voir plus) together with NOTCH1 and pre-T cell receptor (TCR) signalling. Importantly, perturbations of early T-cell regulatory networks are implicated in leukemogenesis. NOTCH1 gain of function mutations invariably lead to T-cell acute lymphoblastic leukemia (T-ALL), whereas inhibition of E proteins accelerates leukemogenesis. Thus, NOTCH1, pre-TCR, E2A and HEB functions are intertwined, but how these pathways contribute individually or synergistically to leukemogenesis remain to be documented. To directly address these questions, we leveraged Cd3e-deficient mice in which pre-TCR signaling and progression through β-selection is abrogated to dissect and decouple the roles of pre-TCR, NOTCH1, E2A and HEB in SCL/TAL1-induced T-ALL, via the use of Notch1 gain of function transgenic (Notch1ICtg) and Tcf12+/- or Tcf3+/- heterozygote mice. As a result, we now provide evidence that both HEB and E2A restrain cell proliferation at the β-selection checkpoint while the clonal expansion of SCL-LMO1-induced pre-leukemic stem cells in T-ALL is uniquely dependent on Tcf12 gene dosage. At the molecular level, HEB protein levels are decreased via proteasomal degradation at the leukemic stage, pointing to a reversible loss of function mechanism. Moreover, in SCL-LMO1-induced T-ALL, loss of one Tcf12 allele is sufficient to bypass pre-TCR signaling which is required for Notch1 gain of function mutations and for progression to T-ALL. In contrast, Tcf12 monoallelic deletion does not accelerate Notch1IC-induced T-ALL, indicating that Tcf12 and Notch1 operate in the same pathway. Finally, we identify a tumor suppressor gene set downstream of HEB, exhibiting significantly lower expression levels in pediatric T-ALL compared to B-ALL and brain cancer samples, the three most frequent pediatric cancers. In summary, our results indicate a tumor suppressor function of HEB/TCF12 in T-ALL to mitigate cell proliferation controlled by NOTCH1 in pre-leukemic stem cells and prevent NOTCH1-driven progression to T-ALL.
2022-03-23
Frontiers in Immunology (publié)
doi.org
From Generative Models to Generative Passages: A Computational Approach to (Neuro) Phenomenology
Maxwell J. D. Ramstead
Anil K. Seth
Casper Hesp
Lars Sandved-Smith
Jonas Mago
Michael Lifshitz
Giuseppe Pagnoni
Ryan Smith
Guillaume Dumas
Antoine Lutz
Karl Friston
Axel Constant
This paper presents a version of neurophenomenology based on generative modelling techniques developed in computational neuroscience and bio… (voir plus)logy. Our approach can be described as computational phenomenology because it applies methods originally developed in computational modelling to provide a formal model of the descriptions of lived experience in the phenomenological tradition of philosophy (e.g., the work of Edmund Husserl, Maurice Merleau-Ponty, etc.). The first section presents a brief review of the overall project to naturalize phenomenology. The second section presents and evaluates philosophical objections to that project and situates our version of computational phenomenology with respect to these projects. The third section reviews the generative modelling framework. The final section presents our approach in detail. We conclude by discussing how our approach differs from previous attempts to use generative modelling to help understand consciousness. In summary, we describe a version of computational phenomenology which uses generative modelling to construct a computational model of the inferential or interpretive processes that best explain this or that kind of lived experience.
2022-03-17
Review of Philosophy and Psychology (publié)
doi.org
Mapping parallelism in a functional IR through constraint satisfaction: a case study on convolution for mobile GPUs
Naums Mogers
Li Li
Valentin Radu
Christophe Dubach
Graphics Processing Units (GPUs) are notoriously hard to optimize for manually. What is needed are good automatic code generators and optimi… (voir plus)zers. Accelerate, Futhark and Lift demonstrated that a functional approach is well suited for this challenge. Lift, for instance, uses a system of rewrite rules with a multi-stage approach. Algorithmic optimizations are first explored, followed by hardware-specific optimizations such as using shared memory and mapping parallelism. While the algorithmic exploration leads to correct transformed programs by construction, it is not necessarily true for the latter phase. Exploiting shared memory and mapping parallelism while ensuring correct synchronization is a delicate balancing act, and is hard to encode in a rewrite system. Currently, Lift relies on heuristics with ad-hoc mechanisms to check for correctness. Although this practical approach eventually produces high-performance code, it is not an ideal state of affairs. This paper proposes to extract parallelization constraints automatically from a functional IR and use a solver to identify valid rewriting. Using a convolutional neural network on a mobile GPU as a use case, this approach matches the performance of the ARM Compute Library GEMM convolution and the TVM-generated kernel consuming between 2.7x and 3.6x less memory on average. Furthermore, a speedup of 12x is achieved over the ARM Compute Library direct convolution implementation.
2022-03-17
Proceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction (publié)
doi.org
WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series Tasks
Jean-christophe Gagnon-audet
Kartik Ahuja
Mohammad Javad Darvishi Bayazi
Guillaume Dumas
Irina Rish
2022-03-17
arXiv (prépublication)
doi.org
arxiv.org
Trips and neurotransmitters: Discovering principled patterns across 6850 hallucinogenic experiences
Galen Ballentine
Samuel Freesun Friedman
Danilo Bzdok
Psychedelics probably alter states of consciousness by disrupting how the higher association cortex governs bottom-up sensory signals. Indiv… (voir plus)idual hallucinogenic drugs are usually studied in participants in controlled laboratory settings. Here, we have explored word usage in 6850 free-form testimonials about 27 drugs through the prism of 40 neurotransmitter receptor subtypes, which were then mapped to three-dimensional coordinates in the brain via their gene transcription levels from invasive tissue probes. Despite high interindividual variability, our pattern-learning approach delineated how drug-induced changes of conscious awareness are linked to cortex-wide anatomical distributions of receptor density proxies. Each discovered receptor-experience factor spanned between a higher-level association pole and a sensory input pole, which may relate to the previously reported collapse of hierarchical order among large-scale networks. Coanalyzing many psychoactive molecules and thousands of natural language descriptions of drug experiences, our analytical framework finds the underlying semantic structure and maps it directly to the brain.
2022-03-15
Science Advances (publié)
doi.org
<i>APOE</i> ɛ2 vs <i>APOE</i> ɛ4 dosage shows sex-specific links to hippocampus-default network subregion co-variation
Chloé Savignac
Sylvia Villeneuve
AmanPreet Badhwar
Karin Saltoun
Kimia Shafighi
Chris Zajner
Vaibhav Sharma
Sarah A Gagliano Taliun
Sali Farhan
Judes Poirier
Danilo Bzdok
Alzheimer’s disease and related dementias (ADRD) are marked by intracellular tau aggregates in the medial-temporal lobe (MTL) and extracel… (voir plus)lular amyloid aggregates in the default network (DN). Here, we sought to clarify ADRD-related co-dependencies between the MTL’s most vulnerable structure, the hippocampus (HC), and the highly associative DN at a subregion resolution. We confronted the effects of APOE ɛ2 and ɛ4, rarely investigated together, with their impact on HC-DN co-variation regimes at the population level. In a two-pronged decomposition of structural brain scans from ∼40,000 UK Biobank participants, we located co-deviating structural patterns in HC and DN subregions as a function of ADRD family risk. Across the disclosed HC-DN signatures, recurrent deviations in the CA1, CA2/3, molecular layer, fornix’s fimbria, and their cortical partners related to ADRD risk. Phenome-wide profiling of HC-DN co- variation expressions from these population signatures revealed male-specific associations with air-pollution, and female-specific associations with cardiovascular traits. We highlighted three main factors associated with brain-APOE associations across the different gene variants: happiness, and satisfaction with friendships, and with family. We further showed that APOE ɛ2/2 interacts preferentially with HC-DN co-variation patterns in estimating social lifestyle in males and physical activity in females. Our findings reinvigorate the often-neglected interplay between APOE ɛ2 dosage and sex, which we have linked to fine-grained structural divergences indicative of ADRD susceptibility.
2022-03-14
bioRxiv (prépublication)
doi.org
Medical Image Segmentation on MRI Images with Missing Modalities: A Review
Reza Azad
Nika Khosravi
Mohammad Dehghanmanshadi
Julien Cohen-Adad
Dorit Merhof
2022-03-10
ArXiv (prépublication)
doi.org
arxiv.org
A New Era: Intelligent Tutoring Systems Will Transform Online Learning for Millions
Francois St-Hilaire
Dung D. Vu
Antoine Frau
Nathan J. Burns
Farid Faraji
Joseph Potochny
Stephane Robert
Arnaud Roussel
Selene Zheng
Taylor Glazier
Junfel Vincent Romano
Robert Belfer
Muhammad Shayan
Ariella Smofsky
Tommy Delarosbil
Seulmin Ahn
Simon Eden-Walker
Kritika Sony
Ansona Onyi Ching
Sabina Elkins … (voir 11 de plus)
A. Stepanyan
Adela Matajova
Victor Chen
Hossein Sahraei
Robert Larson
N. Markova
Andrew Barkett
Laurent Charlin
Yoshua Bengio
Iulian V. Serban
Ekaterina Kochmar
2022-03-02
ArXiv (prépublication)
doi.org
arxiv.org
On Lyapunov Exponents for RNNs: Understanding Information Propagation Using Dynamical Systems Tools
Ryan Vogt
Maximilian Puelma Touzel
Eli Shlizerman
Guillaume Lajoie
Recurrent neural networks (RNNs) have been successfully applied to a variety of problems involving sequential data, but their optimization i… (voir plus)s sensitive to parameter initialization, architecture, and optimizer hyperparameters. Considering RNNs as dynamical systems, a natural way to capture stability, i.e., the growth and decay over long iterates, are the Lyapunov Exponents (LEs), which form the Lyapunov spectrum. The LEs have a bearing on stability of RNN training dynamics because forward propagation of information is related to the backward propagation of error gradients. LEs measure the asymptotic rates of expansion and contraction of nonlinear system trajectories, and generalize stability analysis to the time-varying attractors structuring the non-autonomous dynamics of data-driven RNNs. As a tool to understand and exploit stability of training dynamics, the Lyapunov spectrum fills an existing gap between prescriptive mathematical approaches of limited scope and computationally-expensive empirical approaches. To leverage this tool, we implement an efficient way to compute LEs for RNNs during training, discuss the aspects specific to standard RNN architectures driven by typical sequential datasets, and show that the Lyapunov spectrum can serve as a robust readout of training stability across hyperparameters. With this exposition-oriented contribution, we hope to draw attention to this understudied, but theoretically grounded tool for understanding training stability in RNNs.
2022-03-01
Frontiers in Applied Mathematics and Statistics (publié)
doi.org
arxiv.org
Cross-ethnicity/race generalization failure of behavioral prediction from resting-state functional connectivity
Jingwei Li
Danilo Bzdok
Jianzhong Chen
Angela Tam
Leon Qi Rong Ooi
Avram J. Holmes
Tian Ge
Kaustubh R. Patil
Mbemba Jabbi
Simon B. Eickhoff
B.T. Thomas Yeo
Sarah Genon
Algorithmic biases that favor majority populations pose a key challenge to the application of machine learning for precision medicine. Here,… (voir plus) we assessed such bias in prediction models of behavioral phenotypes from brain functional magnetic resonance imaging. We examined the prediction bias using two independent datasets (preadolescent versus adult) of mixed ethnic/racial composition. When predictive models were trained on data dominated by white Americans (WA), out-of-sample prediction errors were generally higher for African Americans (AA) than for WA. This bias toward WA corresponds to more WA-like brain-behavior association patterns learned by the models. When models were trained on AA only, compared to training only on WA or an equal number of AA and WA participants, AA prediction accuracy improved but stayed below that for WA. Overall, the results point to the need for caution and further research regarding the application of current brain-behavior prediction models in minority populations.
2022-02-28
Science Advances (publié)
doi.org