A new Spectral Riemannian Alignment Score (S-RAS) based on expected projected Fisher metrics quantifies local sensitivity in neural representations and supports layer matching, training dissociations, and brain data analysis.
Understanding image representations by measuring their equivariance and equivalence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Activation Alignment: The Geometry of Neural Sensitivity
A new Spectral Riemannian Alignment Score (S-RAS) based on expected projected Fisher metrics quantifies local sensitivity in neural representations and supports layer matching, training dissociations, and brain data analysis.