Publications

Reinforcement Learning with Elastic Time Steps

Yong Wang

Giovanni Beltrame

2024-02-21

ArXiv (preprint)

doi.org

arxiv.org

Searching for Strong Gravitational Lenses

Cameron Lemon

Frederic Courbin

Anupreeta More

Paul Schechter

Raoul Cañameras

Ludovic Delchambre

Calvin Leung

Yiping Shu

Chiara Spiniello

Yashar Hezaveh

Jonas Klüter

Richard G. McMahon

2024-02-20

Space Science Reviews (published)

doi.org

arxiv.org

Structural covariation between cerebellum and neocortex intrinsic structural covariation links cerebellum subregions to the cerebral cortex

Zilong Wang

Jörn Diedrichsen

Karin Saltoun

Christopher Steele

Sheeba Rani Arnold-Anteraper

B. T. Thomas Yeo

Jeremy D. Schmahmann

Danilo Bzdok

Cerebellum’s association with the entire cerebral cortex has not been holistically studied in a unified way. Here, we conjointly character… (see more)ize the population-level cortical-cerebellar structural covariation patterns leveraging ∼40,000 UK Biobank participants whole brain structural scans and ∼1,000 phenotypes. We revitalize the previous hypothesis of an anticorrelation between the visual-attention system and advanced associative networks within the cerebellum. We also discovered a novel ipsilateral cerebral-cerebellar associations. Phenome-wide association (PheWAS) revealed real-world implications of the structural covariation patterns.

2024-02-19

bioRxiv (preprint)

doi.org

Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks

Sitao Luan

Mingde Zhao

Xiao-Wen Chang

Doina Precup

2024-02-19

Complex Networks & Their Applications XII (published)

doi.org

arxiv.org

Deep Reinforcement Learning in Human Activity Recognition: A Survey and Outlook.

Bahareh Nikpour

Dimitrios Sinodinos

Narges Armanfard

Human activity recognition (HAR) is a popular research field in computer vision that has already been widely studied. However, it is still a… (see more)n active research field since it plays an important role in many current and emerging real-world intelligent systems, like visual surveillance and human-computer interaction. Deep reinforcement learning (DRL) has recently been used to address the activity recognition problem with various purposes, such as finding attention in video data or obtaining the best network structure. DRL-based HAR has only been around for a short time, and it is a challenging, novel field of study. Therefore, to facilitate further research in this area, we have constructed a comprehensive survey on activity recognition methods that incorporate DRL. Throughout the article, we classify these methods according to their shared objectives and delve into how they are ingeniously framed within the DRL framework. As we navigate through the survey, we conclude by shedding light on the prominent challenges and lingering questions that await the attention of future researchers, paving the way for further advancements and breakthroughs in this exciting domain.

2024-02-18

IEEE Transactions on Neural Networks and Learning Systems (published)

doi.org

Virtual Reality for Pediatric Trauma Education - A Face and Content Validation Study

Fabio Botelho

Said Ashkar

Shreenik Kundu

TJ Matthews

Elena Guadgano

Jason Harley

Dan Poenaru

Purpose: Pediatric trauma is a leading cause of death and disability among children. While trauma education can improve these outcomes, it r… (see more)emains expensive and available only to a few providers worldwide. Innovative educational technologies like virtual reality (VR) can be key to democratizing trauma education. This study, therefore, evaluates the face and content validity of a VR platform designed to enhance pediatric trauma skills. Specifically, we seek to determine whether the platform effectively presents an injured child and comprehensively covers the essential tasks to successfully treat them within a trauma team. Methods: Physicians were invited to test a VR platform simulating a child with blunt head and truncal trauma. After the simulation, they filled out surveys assessing the face and content validity of the scenario, including their opinions on the realism, interaction, ease of use, and the educational content of the platform. Additionally, they completed a cybersickness questionnaire. Demographic data were also collected, including age, gender, country of medical education, and previous experience with VR. A descriptive analysis was performed. Results: Eleven physicians graduated from eight different countries tested the VR platform. Most (87%) found it valuable, and 81% preferred using it over high-fidelity mannequins for training purposes. The platform received more favorable evaluations for non-technical skills training (median: 5, IQR: 5.0 to 5.0) than for technical skills (median: 4, IQR: 3.0 to 5.0). Regarding cybersickness, 73% of the participants reported experiencing any or minimal discomfort during the simulation, and none needed to stop the test due to discomfort. Conclusion: Our initial validation of a VR platform designed for pediatric trauma education was positive. Participants endorsed VR and its potential to enhance performance, particularly in non-technical skills. Encouraged by these results, we will proceed with feasibility and implementation studies, comparing VR to high-fidelity mannequins.

2024-02-17

MedRxiv (preprint)

doi.org

Multi-ancestry polygenic risk scores using phylogenetic regularization

Accurately predicting phenotype using genotype across diverse ancestry groups remains a significant challenge in human genetics. Many state-… (see more)of-the-art polygenic risk score models are known to have difficulty generalizing to genetic ancestries that are not well represented in their training set. To address this issue, we present a novel machine learning method for fitting genetic effect sizes across multiple ancestry groups simultaneously, while leveraging prior knowledge of the evolutionary relationships among them. We introduce DendroPRS, a machine learning model where SNP effect sizes are allowed to evolve along the branches of the phylogenetic tree capturing the relationship among populations. DendroPRS outperforms existing approaches at two important genotype-to-phenotype prediction tasks: expression QTL analysis and polygenic risk scores. We also demonstrate that our method can be useful for multi-ancestry modelling, both by fitting population-specific effect sizes and by more accurately accounting for covariate effects across groups. We additionally find a subset of genes where there is strong evidence that an ancestry-specific approach improves eQTL modelling.

2024-02-16

bioRxiv (preprint)

doi.org

Deep Equilibrium Models For Algorithmic Reasoning

Andreea Deac

In this blogpost we discuss the idea of teaching neural networks to reach fixed points when reasoning. Specifically, on the algorithmic reas… (see more)oning benchmark CLRS the current neural networks are told the number of reasoning steps they need. While a quick fix is to add a termination network that predicts when to stop, a much more salient inductive bias is that the neural network shouldn't change it's answer any further once the answer is correct, i.e. it should reach a fixed point. This is supported by denotational semantics, which tells us that while loops that terminate are the minimum fixed points of a function. We implement this idea with the help of deep equilibrium models and discuss several hurdles one encounters along the way. We show on several algorithms from the CLRS benchmark the partial success of this approach and the difficulty in making it work robustly across all algorithms.

2024-02-15

ICLR.cc/2024/BlogPosts (accepted)

openreview.net

Distributional GFlowNets with Quantile Flows

Ricky T. Q. Chen

Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating com… (see more)plex combinatorial structure through a series of decision-making steps. Despite being inspired from reinforcement learning, the current GFlowNet framework is relatively limited in its applicability and cannot handle stochasticity in the reward function. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. By parameterizing each edge flow through their quantile functions, our proposed \textit{quantile matching} GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty. Moreover, we find that the distributional approach can achieve substantial improvement on existing benchmarks compared to prior methods due to our enhanced training algorithm, even in settings with deterministic rewards.

2024-02-15

TMLR (accepted)

doi.org

openreview.net

Diagnosis Model for Detection of e-threats Against Soft-Targets

Sónia M. A. Morgado

Margarida Carvalho

Sérgio Felgueiras

2024-02-13

Lecture Notes in Networks and Systems (published)

doi.org

Computing Power and the Governance of Artificial Intelligence

Girish Sastry

Lennart Heim

Haydn Belfield

Markus Anderljung

Miles Brundage

Julian Hazell

Cullen C. O'keefe

Gillian K. Hadfield

Richard Ngo

Konstantin Pilz

George Gor

Emma Bluemke

Sarah Shoker

Janet Egan

Robert Trager

Shahar Avin

Adrian Weller

Yoshua Bengio

Diane Coyle

Computing power, or"compute,"is crucial for the development and deployment of artificial intelligence (AI) capabilities. As a result, govern… (see more)ments and companies have started to leverage compute as a means to govern AI. For example, governments are investing in domestic compute capacity, controlling the flow of compute to competing countries, and subsidizing compute access to certain sectors. However, these efforts only scratch the surface of how compute can be used to govern AI development and deployment. Relative to other key inputs to AI (data and algorithms), AI-relevant compute is a particularly effective point of intervention: it is detectable, excludable, and quantifiable, and is produced via an extremely concentrated supply chain. These characteristics, alongside the singular importance of compute for cutting-edge AI models, suggest that governing compute can contribute to achieving common policy objectives, such as ensuring the safety and beneficial use of AI. More precisely, policymakers could use compute to facilitate regulatory visibility of AI, allocate resources to promote beneficial outcomes, and enforce restrictions against irresponsible or malicious AI development and usage. However, while compute-based policies and technologies have the potential to assist in these areas, there is significant variation in their readiness for implementation. Some ideas are currently being piloted, while others are hindered by the need for fundamental research. Furthermore, naive or poorly scoped approaches to compute governance carry significant risks in areas like privacy, economic impacts, and centralization of power. We end by suggesting guardrails to minimize these risks from compute governance.

2024-02-12

ArXiv (preprint)

doi.org

arxiv.org

LLMs and Stack Overflow discussions: Reliability, impact, and challenges

Leuson Da Silva

Jordan Samhi

Foutse Khomh

2024-02-12

ArXiv (preprint)

doi.org

arxiv.org