Deep networks are framed as memory spaces whose complexity is defined by a Fisher metric, with the least action principle linking this complexity to generalization and disentanglement for better interpretability.
Deconstructing lottery tickets: zeros, signs, and the supermask
2 Pith papers cite this work, alongside 107 external citations. Polarity classification is still indexing.
2
Pith papers citing it
107
external citations · external index
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Thesis uses statistical mechanics to study DAM and RBM models for understanding memorization, low-dimensional learning, and adversarial robustness in neural networks.
citing papers explorer
-
Deep network as memory space: complexity, generalization, disentangled representation and interpretability
Deep networks are framed as memory spaces whose complexity is defined by a Fisher metric, with the least action principle linking this complexity to generalization and disentanglement for better interpretability.
-
Explaining Machine Learning and Memorization with Statistical Mechanics
Thesis uses statistical mechanics to study DAM and RBM models for understanding memorization, low-dimensional learning, and adversarial robustness in neural networks.