A multi-scale extension of the Fisher information metric, derived from coarse-graining contraction rules, exactly captures the structure of mutual information in neural population codes and can be estimated via diffusion models.
Deep residual learning for im- age recognition
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
verdicts
UNVERDICTED 8representative citing papers
WONN is a new oscillatory neural network based on generalized Winfree dynamics that scales competitively to ImageNet-1K and reaches 80.1% accuracy on Maze-hard with 1% of prior model parameters.
The authors propose target-space recovery profiles to diagnose which reproducible dimensions of fMRI brain responses are captured by model predictions, showing that accuracy alone can mask alignment mismatches in visual cortex.
Target-aligned data selection via normalized endpoint loss drop on a validation-induced reference path achieves competitive performance with reduced computational overhead.
Contextual Plackett-Luce extends the classical Plackett-Luce model with context-dependent Ising parameterization to enable efficient parallel scoring followed by incremental autoregressive selection for ambiguous sequence tasks.
VISTA adaptively tunes consistency thresholds in decentralized SGD so that the system converges asymptotically like standard SGD even when adversaries dominate the worker pool.
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.
Z-Score Filtered SAM retains only high absolute Z-score gradient components per layer during the ascent step and reports higher test accuracy than standard SAM on CIFAR and Tiny-ImageNet benchmarks.
citing papers explorer
-
A multi-scale information geometry reveals the structure of mutual information in neural populations
A multi-scale extension of the Fisher information metric, derived from coarse-graining contraction rules, exactly captures the structure of mutual information in neural population codes and can be estimated via diffusion models.
-
Winfree Oscillatory Neural Network
WONN is a new oscillatory neural network based on generalized Winfree dynamics that scales competitively to ImageNet-1K and reaches 80.1% accuracy on Maze-hard with 1% of prior model parameters.
-
Beyond Prediction Accuracy: Target-Space Recovery Profiles for Evaluating Model-Brain Alignment
The authors propose target-space recovery profiles to diagnose which reproducible dimensions of fMRI brain responses are captured by model predictions, showing that accuracy alone can mask alignment mismatches in visual cortex.
-
Let the Target Select for Itself: Data Selection via Target-Aligned Paths
Target-aligned data selection via normalized endpoint loss drop on a validation-induced reference path achieves competitive performance with reduced computational overhead.
-
Contextual Plackett-Luce: An Efficient Neural Model for Probabilistic Sequence Selection under Ambiguity
Contextual Plackett-Luce extends the classical Plackett-Luce model with context-dependent Ising parameterization to enable efficient parallel scoring followed by incremental autoregressive selection for ambiguous sequence tasks.
-
\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments
VISTA adaptively tunes consistency thresholds in decentralized SGD so that the system converges asymptotically like standard SGD even when adversaries dominate the worker pool.
-
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.
-
Sharpness-Aware Minimization with Z-Score Gradient Filtering
Z-Score Filtered SAM retains only high absolute Z-score gradient components per layer during the ascent step and reports higher test accuracy than standard SAM on CIFAR and Tiny-ImageNet benchmarks.