10 papers
Bracketing Uncertainty in Clustering Under the Manifold Hypothesis
Savik Kinger, Luciano Dyballa, Steven W. Zucker
The manifold hypothesis suggests a natural criterion for clustering: partition data according to the manifold component from which each point is drawn. Whether two components are s…
Decoding Alignment without Encoding Alignment: A critique of similarity analysis in neuroscience
Johannes Bertram, Luciano Dyballa, T. Anderson Keller +2
RSA and CKA are standard metrics for comparing neural representations across brain regions, organisms, and deep learning models. We demonstrate a fundamental weakness: these decodi…
NeuroAI and Beyond: Bridging Between Advances in Neuroscience and Artificial Intelligence
Anthony Zador, Jean-Marc Fellous, Terrence Sejnowski +28
Neuroscience and Artificial Intelligence (AI) have made impressive progress in recent years but remain only loosely interconnected. Based on a workshop convened by the National Sci…
Inferring Active Neural Circuits Using Diffusion Scores
Savik Kinger, Johannes Bertram, Luciano Dyballa +2
In biological systems, neural circuits compute through directed, short-latency interactions whose effects unfold across multiple time scales and behavioral contexts. We address the…
How 'Neural' is a Neural Foundation Model?
Johannes Bertram, Luciano Dyballa, Anderson Keller +2
Foundation models have shown remarkable success in fitting biological visual systems; however, their black-box nature inherently limits their utility for understanding brain functi…
Manifolds and Modules: How Function Develops in a Neural Foundation Model
Johannes Bertram, Luciano Dyballa, T. Anderson Keller +2
Foundation models have shown remarkable success in fitting biological visual systems; however, their black-box nature inherently limits their utility for understanding brain functi…
Individuation of 3D perceptual units from neurogeometry of binocular cells
Maria Virginia Bolelli, Giovanna Citti, Alessandro Sarti +1
We model the functional architecture of the early stages of three-dimensional vision by extending the neurogeometric sub-Riemannian model for stereo-vision introduced in \cite{BCSZ…
A separability-based approach to quantifying generalization: which layer is best?
Luciano Dyballa, Evan Gerritz, Steven W. Zucker
Generalization to unseen data remains poorly understood for deep learning classification and foundation models, especially in the open set scenario. How can one assess the ability…
Learning dynamic representations of the functional connectome in neurobiological networks
Luciano Dyballa, Samuel Lang, Alexandra Haslund-Gourley +2
The static synaptic connectivity of neuronal circuits stands in direct contrast to the dynamics of their function. As in changing community interactions, different neurons can part…
Zero-shot generalization across architectures for visual classification
Evan Gerritz, Luciano Dyballa, Steven W. Zucker
Generalization to unseen data is a key desideratum for deep networks, but its relation to classification accuracy is unclear. Using a minimalist vision dataset and a measure of gen…