Publications

A neuronal least-action principle for real-time learning in cortical circuits
Walter Senn
Dominik Dold
Akos F. Kungl
Benjamin Ellenberger
Jakob Jordan
Yoshua Bengio
João Sacramento
Mihai A. Petrovici
One of the most fundamental laws of physics is the principle of least action. Motivated by its predictive power, we introduce a neuronal lea… (see more)st-action principle for cortical processing of sensory streams to produce appropriate behavioural outputs in real time. The principle postulates that the voltage dynamics of cortical pyramidal neurons prospectively minimize the local somato-dendritic mismatch error within individual neurons. For motor output neurons, it implies minimizing an instantaneous behavioural error. For deep network neurons, it implies a prospective firing to overcome integration delays and correct for possible output errors right in time. The neuron-specific errors are extracted in the apical dendrites of pyramidal neurons through a cortical microcircuit that tries to explain away the feedback from the periphery, and correct the trajectory on the fly. Any motor output is in a moving equilibrium with the sensory inputs and the motor feedback during the whole sensory-motor trajectory. Ongoing synaptic plasticity reduces the somato-dendritic mismatch error within each cortical neuron and performs gradient descent on the output cost at any moment in time. The neuronal least-action principle offers an axiomatic framework to derive local neuronal and synaptic dynamics for global real-time computation and learning in the brain and in physical substrates in general.
2024-12-20
eLife (published)
doi.org
Non-Uniform Parameter-Wise Model Merging
Albert Manuel Orozco Camacho
Stefan Horoi
Guy Wolf
Eugene Belilovsky
Combining multiple machine learning models has long been a technique for enhancing performance, particularly in distributed settings. Tradit… (see more)ional approaches, such as model ensembles, work well, but are expensive in terms of memory and compute. Recently, methods based on averaging model parameters have achieved good results in some settings and have gained popularity. However, merging models initialized differently that do not share a part of their training trajectories can yield worse results than simply using the base models, even after aligning their neurons. In this paper, we introduce a novel approach, Non-uniform Parameter-wise Model Merging, or NP Merge, which merges models by learning the contribution of each parameter to the final model using gradient-based optimization. We empirically demonstrate the effectiveness of our method for merging models of various architectures in multiple settings, outperforming past methods. We also extend NP Merge to handle the merging of multiple models, showcasing its scalability and robustness.
2024-12-20
ArXiv (preprint)
arxiv.org
arxiv.org
Roboethics for everyone – A hands-on teaching module for K-12 and beyond
Rahatul Amin Ananto
Shalaleh Rismani
Lixiao Zhu
Christopher Yee Wong
AJung Moon
In this work, we address the evolving landscape of roboethics, expanding beyond physical safety to encompass broader societal implications. … (see more)Recognizing the siloed nature of existing initiatives to teach and inform ethical implications of artificial intelligence (AI) and robotic systems, we present a roboethics teaching module designed for K-12 students and general audiences. The module focuses on the high-level analysis of the interplay between robot behaviour design choices and ethics, using everyday social dilemmas. We delivered the module in a workshop to high school students in Montreal, Canada. From this experience, we observed that the module successfully fostered critical thinking and ethical considerations in students, without requiring advanced technical knowledge. This teaching module holds promise to reach a wider range of populations. We urge the education community to explore similar approaches and engage in interdisciplinary training opportunities regarding the ethical implications of AI and robotics.
2024-12-20
Proceedings of the Canadian Engineering Education Association (CEEA) (published)
doi.org
Roboethics for everyone – A hands-on teaching module for K-12 and beyond
Rahatul Amin Ananto
Shalaleh Rismani
Lixiao Zhu
Christopher Yee Wong
AJung Moon
In this work, we address the evolving landscape of roboethics, expanding beyond physical safety to encompass broader societal implications. … (see more)Recognizing the siloed nature of existing initiatives to teach and inform ethical implications of artificial intelligence (AI) and robotic systems, we present a roboethics teaching module designed for K-12 students and general audiences. The module focuses on the high-level analysis of the interplay between robot behaviour design choices and ethics, using everyday social dilemmas. We delivered the module in a workshop to high school students in Montreal, Canada. From this experience, we observed that the module successfully fostered critical thinking and ethical considerations in students, without requiring advanced technical knowledge. This teaching module holds promise to reach a wider range of populations. We urge the education community to explore similar approaches and engage in interdisciplinary training opportunities regarding the ethical implications of AI and robotics.
2024-12-20
Proceedings of the Canadian Engineering Education Association (CEEA) (published)
doi.org
Robust Guided Diffusion for Offline Black-Box Optimization
Can Chen
Christopher Beckham
Zixuan Liu
Xue (Steve) Liu
Chris Pal
Offline black-box optimization aims to maximize a black-box function using an offline dataset of designs and their measured properties. Two … (see more)main approaches have emerged: the forward approach, which learns a mapping from input to its value, thereby acting as a proxy to guide optimization, and the inverse approach, which learns a mapping from value to input for conditional generation. (a) Although proxy-free~(classifier-free) diffusion shows promise in robustly modeling the inverse mapping, it lacks explicit guidance from proxies, essential for generating high-performance samples beyond the training distribution. Therefore, we propose \textit{proxy-enhanced sampling} which utilizes the explicit guidance from a trained proxy to bolster proxy-free diffusion with enhanced sampling control. (b) Yet, the trained proxy is susceptible to out-of-distribution issues. To address this, we devise the module \textit{diffusion-based proxy refinement}, which seamlessly integrates insights from proxy-free diffusion back into the proxy for refinement. To sum up, we propose \textit{\textbf{R}obust \textbf{G}uided \textbf{D}iffusion for Offline Black-box Optimization}~(\textbf{RGD}), combining the advantages of proxy~(explicit guidance) and proxy-free diffusion~(robustness) for effective conditional generation. RGD achieves state-of-the-art results on various design-bench tasks, underscoring its efficacy. Our code is at https://anonymous.4open.science/r/RGD-27A5/README.md.
2024-12-20
TMLR (accepted)
doi.org
openreview.net
Editorial: Special Issue on Software Engineering and AI for Data Quality
Foutse Khomh
Andreas Metzger
Phu H. Nguyen
Sagar Sen
This editorial summarizes the content of the Special Issue on Software Engineering and AI for Data Quality of the Journal of Data and Inform… (see more)ation Quality (JDIQ).
2024-12-19
Journal of Data and Information Quality (published)
doi.org
Editorial: Special Issue on Software Engineering and AI for Data Quality
Foutse Khomh
Andreas Metzger
Phu Nguyen
Sagar Sen
This editorial summarizes the content of the Special Issue on Software Engineering and AI for Data Quality of the Journal of Data and Inform… (see more)ation Quality (JDIQ).
2024-12-19
Journal of Data and Information Quality (published)
doi.org
Editorial: Special Issue on Software Engineering and AI for Data Quality
Foutse Khomh
Andreas Metzger
Phu Nguyen
Sagar Sen
This editorial summarizes the content of the Special Issue on Software Engineering and AI for Data Quality of the Journal of Data and Inform… (see more)ation Quality (JDIQ).
2024-12-19
Journal of Data and Information Quality (published)
doi.org
Scaling 4D Representations
João Carreira
Dilara Gokay
Michael King
Chuhan Zhang
Ignacio Rocco
Aravindh Mahendran
T. Keck
Joseph Heyward
Skanda Koppula
Etienne Pot
Goker Erdogan
Yana Hasson
Yi Yang
Klaus Greff
Guillaume Le Moing
Sjoerd van Steenkiste
Daniel Zoran
Drew A. Hudson
Pedro V'elez
Luisa F. Polan'ia … (see 15 more)
Luke Friedman
Chris Duvarney
Ross Goroshin
Kelsey Allen
Jacob Walker
Rishabh Kabra
Eric Aboussouan
Jennifer Sun
Thomas Kipf
Carl Doersch
Viorica Puatruaucean
Dima Damen
Pauline Luc
Mehdi S. M. Sajjadi
Andrew Zisserman
Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations… (see more) on semantic-related tasks
2024-12-19
ArXiv (preprint)
doi.org
arxiv.org
Delays in Care for Children With Low Anorectal Malformations in Southwestern Uganda.
Felix Oyania
Caroline Q. Stephens
Sarah Ullrich
Meera Kotagal
Daniel Kisitu
Francis Bajunirwe
Doruk Ozgediz
Dan Poenaru
2024-12-18
Journal of Surgical Research (published)
doi.org
Delays in Care for Children With Low Anorectal Malformations in Southwestern Uganda.
Felix Oyania
Caroline Q. Stephens
Sarah Ullrich
Meera Kotagal
Daniel Kisitu
Francis Bajunirwe
Doruk Ozgediz
Dan Poenaru
2024-12-18
Journal of Surgical Research (published)
doi.org
Delays in Care for Children With Low Anorectal Malformations in Southwestern Uganda.
Felix Oyania
Caroline Q. Stephens
Sarah Ullrich
Meera Kotagal
Daniel Kisitu
Francis Bajunirwe
Doruk Ozgediz
Dan Poenaru
2024-12-18
Journal of Surgical Research (published)
doi.org