Portrait de Claudia Clopath n'est pas disponible

Claudia Clopath

claudia.clopath@mila.quebec
Visiteur de recherche indépendant - University College London
Superviseur⋅e principal⋅e
Guillaume Lajoie
Sujets de recherche
Neurosciences computationnelles

Publications

Overcoming Rank Collapse in Feedback Alignment
Gauthier Boeshertz
Razvan Pascanu
Claudia Clopath
Backpropagation (BP) is widely viewed as biologically implausible, in part because it requires feedback weights to be the transpose of forwa… (voir plus)rd weights for error propagation. Interestingly, when training a network with fixed random feedback weights to circumvent this issue, learning aligns the forward weights with the feedback weights, leading the backpropagated error signal to become an approximation of the standard gradient used by BP. This process, called Feedback Alignment (FA), occurs in MLPs and very shallow CNNs but does not scale well to deeper architectures. In this work, we first investigated differences between BP and FA models, trained on CIFAR10, specifically focusing on the effective rank of the signal. We found that the FA error has a considerably lower rank and hence is constrained to a lower-dimensional subspace compared to BP, limiting exploration of the parameter space. Motivated by this observation, we evaluated two mechanisms for increasing the effective dimensionality of FA: Muon, an optimiser that orthogonalises weight updates; and hidden activity normalisation, which promotes activation orthogonality. Across larger architectures and benchmarks, we find that these methods consistently improve over FA baselines, for example, on CIFAR100 with a Resnet-18, accuracy increases by 9 percentage points. Our results identify low-dimensional gradient dynamics as a key obstacle to scaling FA and suggest that inducing higher-dimensional update geometry is a promising route toward scaling alternatives to backpropagation.
2026-06-08
arXiv (prépublication)
doi.org
arxiv.org
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… (voir plus) 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 (publié)
doi.org
De novo motor learning creates structure in neural activity that shapes adaptation
Joanna C. Chang
Matthew G. Perich
Lee E. Miller
Juan A. Gallego
Claudia Clopath
Animals can quickly adapt learned movements to external perturbations, and their existing motor repertoire likely influences their ease of a… (voir plus)daptation. Long-term learning causes lasting changes in neural connectivity, which shapes the activity patterns that can be produced during adaptation. Here, we examined how a neural population’s existing activity patterns, acquired through de novo learning, affect subsequent adaptation by modeling motor cortical neural population dynamics with recurrent neural networks. We trained networks on different motor repertoires comprising varying numbers of movements, which they acquired following various learning experiences. Networks with multiple movements had more constrained and robust dynamics, which were associated with more defined neural ‘structure’—organization in the available population activity patterns. This structure facilitated adaptation, but only when the changes imposed by the perturbation were congruent with the organization of the inputs and the structure in neural activity acquired during de novo learning. These results highlight trade-offs in skill acquisition and demonstrate how different learning experiences can shape the geometrical properties of neural population activity and subsequent adaptation.
2024-05-13
Nature Communications (publié)
doi.org
De novo motor learning creates structure in neural activity space that shapes adaptation
Joanna C. Chang
Matthew G Perich
Lee Miller
Juan A. Gallego
Claudia Clopath
2023-05-23
bioRxiv (prépublication)
doi.org
Catalyzing next-generation Artificial Intelligence through NeuroAI
Anthony Zador
Blake Aaron Richards
Bence Ölveczky
Sean Escola
Yoshua Bengio
Kwabena Boahen
Matthew Botvinick
Dmitri Chklovskii
Anne Churchland
Claudia Clopath
James DiCarlo
Surya Ganguli
Jeff Hawkins
Konrad Paul Kording
Alexei Koulakov
Yann Lecun
Timothy P Lillicrap
Adam Marblestone
Bruno Olshausen
Alexandre Pouget … (voir 7 de plus)
Cristina Savin
Terrence Sejnowski
Eero Simoncelli
Sara Solla
David Sussillo
Andreas S. Tolias
Doris Tsao
2023-03-21
Nature Communications (publié)
doi.org
arxiv.org
Small, correlated changes in synaptic connectivity may facilitate rapid motor learning
Barbara Feulner
Matthew G Perich
Raeed H. Chowdhury
Lee Miller
Juan A. Gallego
Claudia Clopath
2022-09-01
Nature Communications (publié)
doi.org
Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece
Luke Y. Prince
Roy Henha Eyono
Ellen Boven
Arna Ghosh
Joe Pemberton
Franz Scherr
Claudia Clopath
Rui Ponte Costa
Wolfgang Maass
Blake A. Richards
Cristina Savin
Katharina Anna Wilmes
We provide a brief review of the common assumptions about biological learning with findings from experimental neuroscience and contrast them… (voir plus) with the efficiency of gradient-based learning in recurrent neural networks. The key issues discussed in this review include: synaptic plasticity, neural circuits, theory-experiment divide, and objective functions. We conclude with recommendations for both theoretical and experimental neuroscientists when designing new studies that could help bring clarity to these issues.
2022-04-26
Neurons, Behavior, Data Analysis, and Theory (publié)
doi.org
arxiv.org
A deep learning framework for neuroscience
Blake Aaron Richards
Timothy P Lillicrap
Philippe Beaudoin
Yoshua Bengio
Rafal Bogacz
Amelia Christensen
Claudia Clopath
Rui Ponte Costa
Archy de Berker
Surya Ganguli
Colleen J Gillon
Danijar Hafner
Adam Kepecs
Nikolaus Kriegeskorte
Peter Latham
Grace W. Lindsay
Kenneth D. Miller
Richard Naud
Christopher C. Pack
Panayiota Poirazi … (voir 12 de plus)
Pieter Roelfsema
João Sacramento
Andrew Saxe
Benjamin Scellier
Anna C. Schapiro
Walter Senn
Greg Wayne
Daniel Yamins
Friedemann Zenke
Joel Zylberberg
Denis Therien
Konrad Paul Kording
2019-10-27
Nature Neuroscience (publié)
doi.org