Publications

A neural implementation model of feedback-based motor learning
Barbara Feulner
Matthew G. Perich
Lee E. Miller
Claudia Clopath
Juan A. Gallego
Animals use feedback to rapidly correct ongoing movements in the presence of a perturbation. Repeated exposure to a predictable perturbation… (see more) leads to behavioural adaptation that compensates for its effects. Here, we tested the hypothesis that all the processes necessary for motor adaptation may emerge as properties of a controller that adaptively updates its policy. We trained a recurrent neural network to control its own output through an error-based feedback signal, which allowed it to rapidly counteract external perturbations. Implementing a biologically plausible plasticity rule based on this same feedback signal enabled the network to learn to compensate for persistent perturbations through a trial-by-trial process. The network activity changes during learning matched those from populations of neurons from monkey primary motor cortex — known to mediate both movement correction and motor adaptation — during the same task. Furthermore, our model natively reproduced several key aspects of behavioural studies in humans and monkeys. Thus, key features of trial-by-trial motor adaptation can arise from the internal properties of a recurrent neural circuit that adaptively controls its output based on ongoing feedback.
2025-02-19
Nature Communications (published)
doi.org
OBELiX: a curated dataset of crystal structures and experimentally measured ionic conductivities for lithium solid-state electrolytes
Félix Therrien
Jamal Abou Haibeh
Divya Sharma
Rhiannon Hendley
Leah Wairimu Mungai
Sun Sun
Alain Tchagang
Jiang Su
Samuel Huberman
Yoshua Bengio
Hongyu Guo
Alex Hernández-García
Homin Shin
OBELiX is a database of 599 synthesized solid electrolyte materials and their experimentally measured room temperature ionic conductivities … (see more)gathered from literature and curated by domain experts.
2025-02-19
arXiv (preprint)
doi.org
openreview.net
AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
Shaona Ghosh
Heather Frase
Adina Williams
Sarah Luger
Paul Rottger
Fazl Barez
Sean McGregor
Kenneth Fricklas
Mala Kumar
Quentin Feuillade--Montixi
Kurt Bollacker
Felix Friedrich
Ryan Tsang
Bertie Vidgen
Alicia Parrish
Chris Knotz
Eleonora Presani
Jonathan Bennion
Marisa Ferrara Boston
Mike Kuniavsky … (see 81 more)
Wiebke Hutiri
James Ezick
Malek Ben Salem
Rajat Sahay
Sujata Goswami
Usman Gohar
Ben Huang
Supheakmungkol Sarin
Elie Alhajjar
Canyu Chen
Roman Eng
K. Manjusha
Virendra Mehta
Eileen Peters Long
Murali Krishna Emani
Natan Vidra
Benjamin Rukundo
Abolfazl Shahbazi
Kongtao Chen
Rajat Ghosh
Vithursan Thangarasa
Pierre Peign'e
Abhinav Singh
Max Bartolo
Satyapriya Krishna
Mubashara Akhtar
Rafael Gold
Cody Coleman
Luis Oala
Vassil Tashev
Joseph Marvin Imperial
Amy Russ
Sasidhar Kunapuli
Nicolas Miailhe
Julien Delaunay
Bhaktipriya Radharapu
Rajat Shinde
Tuesday
Debojyoti Dutta
Declan Grabb
Ananya Gangavarapu
Saurav Sahay
Agasthya Gangavarapu
Patrick Schramowski
Stephen Singam
Tom David
Xudong Han
Priyanka Mary Mammen
Tarunima Prabhakar
Venelin Kovatchev
Ahmed M. Ahmed
Kelvin Manyeki
Sandeep Madireddy
Foutse Khomh
Fedor Zhdanov
Joachim Baumann
N. Vasan
Xianjun Yang
Carlos Mougn
Jibin Rajan Varghese
Hussain Chinoy
Seshakrishna Jitendar
Manil Maskey
Claire V. Hardgrove
Tianhao Li
Aakash Gupta
Emil Joswin
Yifan Mai
Shachi H. Kumar
Çigdem Patlak
Kevin Lu
Vincent Alessi
Sree Bhargavi Balija
Chenhe Gu
Robert Sullivan
James Gealy
Matt Lavrisa
James Goel
Peter Mattson
Percy Liang
Joaquin Vanschoren
2025-02-18
ArXiv (preprint)
doi.org
arxiv.org
Cell type transcriptomics reveal shared genetic mechanisms in Alzheimer’s and Parkinson’s disease
Anwesha Bhattacharya
Edward A. Fon
Alain Dagher
Yasser Iturria-Medina
Jo Anne Stratton
Chloé Savignac
Jack Stanley
Liam Hodgson
Badr Ait Hammou
David A Bennett
Danilo Bzdok
Historically, Alzheimer’s disease (AD) and Parkinson’s disease (PD) have been investigated as two distinct disorders of the brain. Howev… (see more)er, a few similarities in neuropathology and clinical symptoms have been documented over the years. Traditional single gene-centric genetic studies, including GWAS and differential gene expression analyses, have struggled to unravel the molecular links between AD and PD. To address this, we tailor a pattern-learning framework to analyze synchronous gene co-expression at sub-cell-type resolution. Utilizing recently published single-nucleus AD (70,634 nuclei) and PD (340,902 nuclei) datasets from postmortem human brains, we systematically extract and juxtapose disease-critical gene modules. Our findings reveal extensive molecular similarities between AD and PD gene cliques. In neurons, disrupted cytoskeletal dynamics and mitochondrial stress highlight convergence in key processes; glial modules share roles in T-cell activation, myelin synthesis, and synapse pruning. This multi-module sub-cell-type approach offers insights into the molecular basis of shared neuropathology in AD and PD.
2025-02-18
bioRxiv (preprint)
doi.org
Cell type transcriptomics reveal shared genetic mechanisms in Alzheimer’s and Parkinson’s disease
Anwesha Bhattacharya
Edward A. Fon
Alain Dagher
Yasser Iturria-Medina
Jo Anne Stratton
Chloé Savignac
Jack Stanley
Liam Hodgson
Badr Ait Hammou
David A Bennett
Danilo Bzdok
Historically, Alzheimer’s disease (AD) and Parkinson’s disease (PD) have been investigated as two distinct disorders of the brain. Howev… (see more)er, a few similarities in neuropathology and clinical symptoms have been documented over the years. Traditional single gene-centric genetic studies, including GWAS and differential gene expression analyses, have struggled to unravel the molecular links between AD and PD. To address this, we tailor a pattern-learning framework to analyze synchronous gene co-expression at sub-cell-type resolution. Utilizing recently published single-nucleus AD (70,634 nuclei) and PD (340,902 nuclei) datasets from postmortem human brains, we systematically extract and juxtapose disease-critical gene modules. Our findings reveal extensive molecular similarities between AD and PD gene cliques. In neurons, disrupted cytoskeletal dynamics and mitochondrial stress highlight convergence in key processes; glial modules share roles in T-cell activation, myelin synthesis, and synapse pruning. This multi-module sub-cell-type approach offers insights into the molecular basis of shared neuropathology in AD and PD.
2025-02-18
bioRxiv : the preprint server for biology (published)
doi.org
Making the Write Connections: Linking Writing Support Tools with Writer Needs
Zixin Zhao
Damien Masson
Young-Ho Kim
Gerald Penn
Fanny Chevalier
2025-02-17
ArXiv (preprint)
doi.org
arxiv.org
Making the Write Connections: Linking Writing Support Tools with Writer's Needs
Zixin Zhao
Damien Masson
Young-Ho Kim
Gerald Penn
Fanny Chevalier
2025-02-17
ArXiv (preprint)
doi.org
arxiv.org
Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives
Leo Schwinn
Yan Scholten
Tom Wollschlager
Sophie Xhonneux
Stephen Casper
Stephan Günnemann
Gauthier Gidel
2025-02-16
ArXiv (preprint)
doi.org
arxiv.org
Automatic Pruning of Fine-tuning Datasets for Transformer-based Language Models
Sayed Mohammadreza Tayaranian Hosseini
Seyyed Hasan Mozafari
Brett H. Meyer
James J. Clark
Warren J. Gross
Transformer-based language models have shown state-of-the-art performance on a variety of natural language understanding tasks. To achieve t… (see more)his performance, these models are first pre-trained on general corpus and then fine-tuned on downstream tasks. Previous work studied the effect of pruning the training set of the downstream tasks on the performance of the model on its evaluation set. In this work, we propose an automatic dataset pruning method for the training set of fine-tuning tasks. Our method is based on the model’s success rate in correctly classifying each training data point. Unlike previous work which relies on user feedback to determine subset size, our method automatically extracts training subsets that are adapted for each pair of model and fine-tuning task. Our method provides multiple subsets for use in dataset pruning that navigate the trade-off between subset size and evaluation accuracy. Our largest subset, which we also refer to as the winning ticket subset, is on average
2025-02-16
Proceedings of The 3rd Conference on Lifelong Learning Agents (published)
proceedings.mlr.press
proceedings.mlr.press
BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages
Shamsuddeen Hassan Muhammad
Nedjma OUSIDHOUM
Idris Abdulmumin
Jan Philip Wahle
Terry Lima Ruas
Meriem Beloucif
Christine de Kock
Nirmal Surange
Daniela Teodorescu
Ibrahim Ahmad
David Ifeoluwa Adelani
Alham Fikri Aji
Felermino Ali
Ilseyar Alimova
Vladimir Araujo
Nikolay Babakov
Naomi Baes
Ana-Maria Bucur
Andiswa Bukula
Guanqun Cao … (see 28 more)
Rodrigo Tufino Cardenas
Rendi Chevi
Chiamaka Ijeoma Chukwuneke
Alexandra Ciobotaru
Daryna Dementieva
Murja Sani Gadanya
Robert Geislinger
Bela Gipp
Oumaima Hourrane
Oana Ignat
Falalu Lawan
Rooweither Mabuya
Rahmad Mahendra
Vukosi Marivate
Andrew Piper
Alexander Panchenko
Charles Henrique Porto Ferreira
Vitaly Protasov
Samuel Rutunda
Manish Shrivastava
Aura Cristina Udrea
Lilian D. A. Wanzare
Sophie Wu
Florian Valentin Wunderlich
Hanif Muhammad Zhafran
Tianhui Zhang
Yi Zhou
Saif M. Mohammad
2025-02-16
ArXiv (preprint)
doi.org
arxiv.org
Channel-Selective Normalization for Label-Shift Robust Test-Time Adaptation
Pedro Vianna
Muawiz Chaudhary
Paria Mehrbod
An Tang
Guy Cloutier
Guy Wolf
Michael Eickenberg
Eugene Belilovsky
Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the … (see more)data distribution. For example, in the biomedical field, their performance can be affected by changes in the data (different machines, populations) between training and test datasets. To ensure robustness and generalization to real-world scenarios, test-time adaptation has been recently studied as an approach to adjust models to a new data distribution during inference. Test-time batch normalization is a simple and popular method that achieved compelling performance on domain shift benchmarks. It is implemented by recalculating batch normalization statistics on test batches. Prior work has focused on analysis with test data that has the same label distribution as the training data. However, in many practical applications this technique is vulnerable to label distribution shifts, sometimes producing catastrophic failure. This presents a risk in applying test time adaptation methods in deployment. We propose to tackle this challenge by only selectively adapting channels in a deep network, minimizing drastic adaptation that is sensitive to label shifts. Our selection scheme is based on two principles that we empirically motivate: (1) later layers of networks are more sensitive to label shift (2) individual features can be sensitive to specific classes. We apply the proposed technique to three classification tasks, including CIFAR10-C, Imagenet-C, and diagnosis of fatty liver, where we explore both covariate and label distribution shifts. We find that our method allows to bring the benefits of TTA while significantly reducing the risk of failure common in other methods, while being robust to choice in hyperparameters.
2025-02-16
Conference on Lifelong Learning Agents (published)
doi.org
proceedings.mlr.press
Characterizing co-purchased food products with soda, fresh fruits, and fresh vegetables using loyalty card purchasing data in Montréal, Canada, 2015–2017
Hiroshi Mamiya
Kody Crowell
Catherine L. Mah
Amélie Quesnel-Vallée
Aman Verma
David L. Buckeridge
Foods are not purchased in isolation but are normally co-purchased with other food products. The patterns of co-purchasing associations acro… (see more)ss a large number of food products have been rarely explored to date. Knowledge of such co-purchasing patterns will help evaluate nutrition interventions that might affect the purchasing of multiple food items while providing insights about food marketing activities that target multiple food items simultaneously. To quantify the association of food products purchased with each of three food categories of public health importance: soda, fresh fruits and fresh vegetables using Association Rule Mining (ARM) followed by longitudinal regression analysis. We obtained transaction data containing grocery purchasing baskets (lists of purchased products) collected from loyalty club members in a major supermarket chain between 2015 and 2017 in Montréal, Canada. There were 72 food groups in these data. ARM was applied to identify food categories co-purchased with soda, fresh fruits, and fresh vegetables. A subset of co-purchasing associations identified by ARM was further tested by confirmatory logistic regression models controlling for potential confounders of the associations and correlated purchasing patterns within shoppers. We analyzed 1,692,716 baskets. Salty snacks showed the strongest co-purchasing association with soda (Relative Risk [RR] = 2.07, 95% Confidence Interval [CI]: 2.06, 2.09). Sweet snacks/candies (RR = 1.73, 95%CI: 1.72–1.74) and juices/drinks (RR:1.71, 95%CI:1.71–1.73) also showed strong co-purchasing associations with soda. Fresh vegetables and fruits showed considerably different patterns of co-purchasing associations from those of soda, with pre-made salad and stir fry showing a strong association (RR = 3.78, 95% CI:3.74–3.82 for fresh vegetables and RR = 2.79, 95%CI:2.76–2.81 for fresh fruits). The longitudinal regression analysis confirmed these associations after adjustment for the confounders, although the associations were weaker in magnitude. Quantifying the interdependence of food products within shopping baskets provides novel insights for developing nutrition surveillance and interventions targeting multiple food categories while motivating research to identify drivers of such co-purchasing. ARM is a useful analytical approach to identify such cross-food associations from retail transaction data when combined with confirmatory regression analysis to adjust for confounders of such associations.
2025-02-16
The International Journal of Behavioral Nutrition and Physical Activity (published)
doi.org