Publications

Sex-specific lesion pattern of functional outcomes after stroke

Anna K. Bonkhoff

Martin Bretzner

Sungmin Hong

Markus D. Schirmer

Alexander Cohen

Robert W. Regenhardt

Kathleen L. Donahue

Marco J. Nardin

Adrian V. Dalca

Anne-Katrin Giese

Mark R. Etherton

Brandon L. Hancock

Steven J. T. Mocking

Elissa C. McIntosh

John Attia

Oscar R. Benavente

Stephen Bevan

John W. Cole

Amanda Donatti

Christoph J. Griessenauer … (see 39 more)

Laura Heitsch

Lukas Holmegaard

Katarina Jood

Jordi Jimenez-Conde

Steven J. Kittner

Robin Lemmens

Christopher R. Levi

Caitrin W. McDonough

James F. Meschia

Chia-Ling Phuah

Arndt Rolfs

Stefan Ropele

Jonathan Rosand

Jaume Roquer

Tatjana Rundek

Ralph L. Sacco

Reinhold Schmidt

Pankaj Sharma

Agnieszka Slowik

Martin Söderholm

Alessandro Sousa

Tara M. Stanne

Daniel Strbian

Turgut Tatlisumak

Vincent Thijs

Achala Vagal

Johan Wasselius

Daniel Woo

Ramin Zand

Patrick F. McArdle

Bradford B. Worrall

Christina Jern

Arne G. Lindgren

Jane Maguire

Michael D. Fox

Danilo Bzdok

Ona Wu

Natalia S. Rost

Anna K. Martin Sungmin Markus D. Alexander Robert W. Kathleen L. Marco J. Adrian V. Anne-Katrin Mark R. Brandon L. Steven J. T. Elissa C. John Oscar R. Stephen John W. Amanda Christoph J. Laura Lukas Katarina Jordi Steven J. Robin Christopher R. Caitrin W. James F. Chia-Ling Arndt Stefan Jonathan Jaume Tatjana Ralph L. Reinhold Pankaj Agnieszka Martin Alessandro Tara M. Daniel Turgut Vincent Achala Johan Daniel Ramin Patrick F. Bradford B. Christina Arne G. Jane Michael D. Danilo Ona Natalia S. Bonkhoff

Stroke represents a considerable burden of disease for both men and women. However, a growing body of literature suggests clinically relevan… (see more)t sex differences in the underlying causes, presentations and outcomes of acute ischaemic stroke. In a recent study, we reported sex divergences in lesion topographies: specific to women, acute stroke severity was linked to lesions in the left-hemispheric posterior circulation. We here determined whether these sex-specific brain manifestations also affect long-term outcomes. We relied on 822 acute ischaemic patients [age: 64.7 (15.0) years, 39% women] originating from the multi-centre MRI-GENIE study to model unfavourable outcomes (modified Rankin Scale >2) based on acute neuroimaging data in a Bayesian hierarchical framework. Lesions encompassing bilateral subcortical nuclei and left-lateralized regions in proximity to the insula explained outcomes across men and women (area under the curve = 0.81). A pattern of left-hemispheric posterior circulation brain regions, combining left hippocampus, precuneus, fusiform and lingual gyrus, occipital pole and latero-occipital cortex, showed a substantially higher relevance in explaining functional outcomes in women compared to men [mean difference of Bayesian posterior distributions (men – women) = −0.295 (90% highest posterior density interval = −0.556 to −0.068)]. Once validated in prospective studies, our findings may motivate a sex-specific approach to clinical stroke management and hold the promise of enhancing outcomes on a population level.

2022-01-30

Brain Communications (published)

doi.org

Age differences in the functional architecture of the human brain

Roni Setton

Laetitia Mwilambwe-Tshilobo

Manesh Girn

Amber W. Lockrow

Giulia Baracchini

Colleen Hughes

Alexander J. Lowe

Benjamin N. Cassidy

Jian Li

Wen-Ming Luh

Danilo Bzdok

Richard M. Leahy

Tian Ge

Daniel S. Margulies

Bratislav Misic

Boris C. Bernhardt

W. Dale Stevens

Felipe De Brigard

Prantik Kundu

Gary R. Turner … (see 2 more)

R. Nathan Spreng

Montreal Neurological

The intrinsic functional organization of the brain changes into older adulthood. Age differences are observed at multiple spatial scales, fr… (see more)om global reductions in modularity and segregation of distributed brain systems, to network-specific patterns of dedifferentiation. Whether dedifferentiation reflects an inevitable, global shift in brain function with age, circumscribed, experience dependent changes, or both, is uncertain. We employed a multi-method strategy to interrogate dedifferentiation at multiple spatial scales. Multi-echo (ME) resting-state fMRI was collected in younger (n=181) and older (n=120) healthy adults. Cortical parcellation sensitive to individual variation was implemented for precision functional mapping of each participant, while preserving group-level parcel and network labels. ME-fMRI processing and gradient mapping identified global and macroscale network differences. Multivariate functional connectivity methods tested for microscale, edge-level differences. Older adults had lower BOLD signal dimensionality, consistent with global network dedifferentiation. Gradients were largely age-invariant. Edge-level analyses revealed discrete, network-specific dedifferentiation patterns in older adults. Visual and somatosensory regions were more integrated within the functional connectome; default and frontoparietal control network regions showed greater connectivity; and the dorsal attention network was more integrated with heteromodal regions. These findings highlight the importance of multi-scale, multi-method approaches to characterize the architecture of functional brain aging.

2022-01-27

Cerebral Cortex (published)

doi.org

Conditional Image Generation by Conditioning Variational Auto-Encoders

William Harvey

Saeid Naderiparizi

Frank N. Wood

We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture … (see more)and training objective capable of leveraging a foundation model in the form of a pretrained unconditional VAE. To train the conditional VAE, we only need to train an artifact to perform amortized inference over the unconditional VAE's latent variables given a conditioning input. We demonstrate our approach on tasks including image inpainting, for which it outperforms state-of-the-art GAN-based approaches at faithfully representing the inherent uncertainty. We conclude by describing a possible application of our inpainting model, in which it is used to perform Bayesian experimental design for the purpose of guiding a sensor.

2022-01-27

ICLR.cc/2022/Conference (poster)

openreview.net

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation

Jongmin Lee

Cosmin Paduraru

Daniel J Mankowitz

Nicolas Heess

Doina Precup

Kee-Eung Kim

Arthur Guez

We consider the offline constrained reinforcement learning (RL) problem, in which the agent aims to compute a policy that maximizes expected… (see more) return while satisfying given cost constraints, learning only from a pre-collected dataset. This problem setting is appealing in many real-world scenarios, where direct interaction with the environment is costly or risky, and where the resulting policy should comply with safety constraints. However, it is challenging to compute a policy that guarantees satisfying the cost constraints in the offline RL setting, since the off-policy evaluation inherently has an estimation error. In this paper, we present an offline constrained RL algorithm that optimizes the policy in the space of the stationary distribution. Our algorithm, COptiDICE, directly estimates the stationary distribution corrections of the optimal policy with respect to returns, while constraining the cost upper bound, with the goal of yielding a cost-conservative policy for actual constraint satisfaction. Experimental results show that COptiDICE attains better policies in terms of constraint satisfaction and return-maximization, outperforming baseline algorithms.

2022-01-27

ICLR.cc/2022/Conference (spotlight)

doi.org

openreview.net

Deep ReLU Networks Preserve Expected Length

Boris Hanin

Ryan Jeong

David Rolnick

Assessing the complexity of functions computed by a neural network helps us understand how the network will learn and generalize. One natura… (see more)l measure of complexity is how the network distorts length - if the network takes a unit-length curve as input, what is the length of the resulting curve of outputs? It has been widely believed that this length grows exponentially in network depth. We prove that in fact this is not the case: the expected length distortion does not grow with depth, and indeed shrinks slightly, for ReLU networks with standard random initialization. We also generalize this result by proving upper bounds both for higher moments of the length distortion and for the distortion of higher-dimensional volumes. These theoretical results are corroborated by our experiments.

2022-01-27

ICLR.cc/2022/Conference (poster)

openreview.net

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization

Aviral Kumar

Rishabh Agarwal

Tengyu Ma

Aaron Courville

George Tucker

Sergey Levine

Despite overparameterization, deep networks trained via supervised learning are surprisingly easy to optimize and exhibit excellent generali… (see more)zation. One hypothesis to explain this is that overparameterized deep networks enjoy the benefits of implicit regularization induced by stochastic gradient descent, which favors parsimonious solutions that generalize well on test inputs. It is reasonable to surmise that deep reinforcement learning (RL) methods could also benefit from this effect. In this paper, we discuss how the implicit regularization effect of SGD seen in supervised learning could in fact be harmful in the offline deep RL setting, leading to poor generalization and degenerate feature representations. Our theoretical analysis shows that when existing models of implicit regularization are applied to temporal difference learning, the resulting derived regularizer favors degenerate solutions with excessive aliasing, in stark contrast to the supervised learning case. We back up these findings empirically, showing that feature representations learned by a deep network value function trained via bootstrapping can indeed become degenerate, aliasing the representations for state-action pairs that appear on either side of the Bellman backup. To address this issue, we derive the form of this implicit regularizer and, inspired by this derivation, propose a simple and effective explicit regularizer, called DR3, that counteracts the undesirable effects of this implicit regularizer. When combined with existing offline RL methods, DR3 substantially improves performance and stability, alleviating unlearning in Atari 2600 games, D4RL domains, and robotic manipulation from images.

2022-01-27

ICLR.cc/2022/Conference (spotlight)

openreview.net

FairCal: Fairness Calibration for Face Verification

Adam Oberman

Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly dep… (see more)ends on sensitive attributes such as the ethnicity of the face. As a result, these models can disproportionately and negatively impact minority groups, particularly when used by law enforcement. The majority of bias reduction methods have several drawbacks: they use an end-to-end retraining approach, may not be feasible due to privacy issues, and often reduce accuracy. An alternative approach is post-processing methods that build fairer decision classifiers using the features of pre-trained models, thus avoiding the cost of retraining. However, they still have drawbacks: they reduce accuracy (AGENDA, PASS, FTC), or require retuning for different false positive rates (FSN). In this work, we introduce the Fairness Calibration (FairCal) method, a post-training approach that simultaneously: (i) increases model accuracy (improving the state-of-the-art), (ii) produces fairly-calibrated probabilities, (iii) significantly reduces the gap in the false positive rates, (iv) does not require knowledge of the sensitive attribute, and (v) does not require retraining, training an additional model, or retuning. We apply it to the task of Face Verification, and obtain state-of-the-art results with all the above advantages.

2022-01-27

International Conference on Learning Representations (poster)

doi.org

openreview.net

Fortuitous Forgetting in Connectionist Networks

Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact b… (see more)e favorable to learning. We introduce "forget-and-relearn" as a powerful paradigm for shaping the learning trajectories of artificial neural networks. In this process, the forgetting step selectively removes undesirable information from the model, and the relearning step reinforces features that are consistently useful under different conditions. The forget-and-relearn framework unifies many existing iterative training algorithms in the image classification and language emergence literature, and allows us to understand the success of these algorithms in terms of the disproportionate forgetting of undesirable information. We leverage this understanding to improve upon existing algorithms by designing more targeted forgetting operations. Insights from our analysis provide a coherent view on the dynamics of iterative training in neural networks and offer a clear path towards performance improvements.

2022-01-27

International Conference on Learning Representations (poster)

doi.org

openreview.net

Integrated pretraining with evolutionary information to improve RNA secondary structure prediction

Zichao Yan

William Hamilton

Mathieu Blanchette

A bstract RNA secondary structure prediction is a fundamental task in … (see more)computational and molecular biology. While machine learning approaches in this area have been shown to improve upon traditional RNA folding algorithms, performance remains limited for several reasons such as the small number of experimentally determined RNA structures and suboptimal use of evolutionary information. To address these challenges, we introduce a practical and effective pretraining strategy that enables learning from a larger set of RNA sequences with computationally predicted structures and in the meantime, tapping into the rich evolutionary information available in databases such as Rfam. Coupled with a flexible and scalable neural architecture that can navigate different learning scenarios while providing ease of integrating evolutionary information, our approach significantly improves upon state-of-the-art across a range of benchmarks, including both single sequence and alignment based structure prediction tasks, with particularly notable benefits on new, less well-studied RNA families. Our source code, data and packaged RNA secondary structure prediction software RSSMFold can be accessed at https://github.com/HarveyYan/RSSMFold .

2022-01-27

bioRxiv (preprint)

doi.org

Learning to Dequantise with Truncated Flows

Dequantisation is a general technique used for transforming data described by a discrete random variable x into a continuous (latent) random… (see more) variable z, for the purpose of it being modeled by likelihood-based density models. Dequantisation was first introduced in the context of ordinal data, such as image pixel values. However, when the data is categorical, the dequantisation scheme is not obvious. We learn such a dequantisation scheme q(z|x), using variational inference with TRUncated FLows (TRUFL) — a novel flow-based model that allows the dequantiser to have a learnable truncated support. Unlike previous work, the TRUFL dequantiser is (i) capable of embedding the data losslessly in certain cases, since the truncation allows the conditional distributions q(z|x) to have non-overlapping bounded supports, while being (ii) trainable with back-propagation. Addtionally, since the support of the marginal q(z) is bounded and the support of prior p(z) is not, we propose to renormalise the prior distribution over the support of q(z). We derive a lower bound for training, and propose a rejection sampling scheme to account for the invalid samples. Experimentally, we benchmark TRUFL on constrained generation tasks, and find that it outperforms prior approaches. In addition, we find that rejection sampling results in higher validity for the constrained problems.

2022-01-27

ICLR.cc/2022/Conference (poster)

openreview.net

Medical Doctors in Health Reforms

Jean-Louis Denis

Sabrina Germain

Catherine Régis

Gianluca Veronesi

Health and legal experts from England and Canada consider the influence of medical doctors on reforms in this comparative study. With reflec… (see more)tions on participation since the inception of publicly funded healthcare systems, they show how the status of doctors affects change.

2022-01-27

(published)

doi.org

R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning

Shengyao Lu

Bang Liu

Keith G Mills

SHANGLING JUI

Di Niu

Systematicity, i.e., the ability to recombine known parts and rules to form new sequences while reasoning over relational data, is critical … (see more)to machine intelligence. A model with strong systematicity is able to train on small-scale tasks and generalize to large-scale tasks. In this paper, we propose R5, a relational reasoning framework based on reinforcement learning that reasons over relational graph data and explicitly mines underlying compositional logical rules from observations. R5 has strong systematicity and being robust to noisy data. It consists of a policy value network equipped with Monte Carlo Tree Search to perform recurrent relational prediction and a backtrack rewriting mechanism for rule mining. By alternately applying the two components, R5 progressively learns a set of explicit rules from data and performs explainable and generalizable relation prediction. We conduct extensive evaluations on multiple datasets. Experimental results show that R5 outperforms various embedding-based and rule induction baselines on relation prediction tasks while achieving a high recall rate in discovering ground truth rules.

2022-01-27

ICLR.cc/2022/Conference (spotlight)

doi.org

openreview.net

Venture Scientist Bootcamp

AI Policy Compass

Supervision Requests

Publications

Venture Scientist Bootcamp

AI Policy Compass

Supervision Requests

Popular keywords:

Publications