Getting aligned on representational alignment

I Sucholutsky, L Muttenthaler, A Weller, A Peng… - arXiv preprint arXiv …, 2023 - arxiv.org
Biological and artificial information processing systems form representations that they can
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …

Computational role of structure in neural activity and connectivity

S Ostojic, S Fusi - Trends in Cognitive Sciences, 2024 - cell.com
One major challenge of neuroscience is identifying structure in seemingly disorganized
neural activity. Different types of structure have different computational implications that can …

Beyond geometry: Comparing the temporal structure of computation in neural circuits with dynamical similarity analysis

M Ostrow, A Eisen, L Kozachkov… - Advances in Neural …, 2024 - proceedings.neurips.cc
How can we tell whether two neural networks utilize the same internal processes for a
particular computation? This question is pertinent for multiple subfields of neuroscience and …

Similarity of neural network models: A survey of functional and representational measures

M Klabunde, T Schumacher, M Strohmaier… - arXiv preprint arXiv …, 2023 - arxiv.org
Measuring similarity of neural networks to understand and improve their behavior has
become an issue of great importance and research interest. In this survey, we provide a …

Estimating noise correlations across continuous conditions with Wishart processes

A Nejatbakhsh, I Garon… - Advances in Neural …, 2024 - proceedings.neurips.cc
The signaling capacity of a neural population depends on the scale and orientation of its
covariance across trials. Estimating this" noise" covariance is challenging and is thought to …

A clustered federated learning framework for collaborative fault diagnosis of wind turbines

R Zhou, Y Li, X Lin - Applied Energy, 2025 - Elsevier
Data-driven approaches demonstrate significant potential in accurately diagnosing faults in
wind turbines. To enhance diagnostic performance and reduce communication costs in …

Hierarchical VAEs provide a normative account of motion processing in the primate brain

H Vafaii, J Yates, D Butts - Advances in Neural Information …, 2024 - proceedings.neurips.cc
The relationship between perception and inference, as postulated by Helmholtz in the 19th
century, is paralleled in modern machine learning by generative models like Variational …

Discriminating image representations with principal distortions

J Feather, D Lipshutz, SE Harvey, AH Williams… - arXiv preprint arXiv …, 2024 - arxiv.org
Image representations (artificial or biological) are often compared in terms of their global
geometry; however, representations with similar global structure can have strikingly different …

Duality of Bures and Shape Distances with Implications for Comparing Neural Representations

SE Harvey, BW Larsen… - Proceedings of UniReps …, 2024 - proceedings.mlr.press
A multitude of (dis) similarity measures between neural networks representations have been
proposed, resulting in a fragmented research landscape. Most (dis) similarity measures fall …

Training objective drives the consistency of representational similarity across datasets

L Ciernik, L Linhardt, M Morik, J Dippel… - arXiv preprint arXiv …, 2024 - arxiv.org
The Platonic Representation Hypothesis claims that recent foundation models are
converging to a shared representation space as a function of their downstream task …