Chaotic dynamics in RNNs induce local roughness but preserve global smoothness in representations, acting as an intrinsic regularizer and generating power-law spectral signatures.
Adaptive kernel predictors from feature-learning infinite limits of neural networks , url =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Review of neural scaling laws and their relation to constraints and inductive biases when applying machine learning to physics problems.
citing papers explorer
-
Discrete signaling mediates chaotic regularization in recurrent neural networks
Chaotic dynamics in RNNs induce local roughness but preserve global smoothness in representations, acting as an intrinsic regularizer and generating power-law spectral signatures.
-
Statistical Properties of Training & Generalization
Review of neural scaling laws and their relation to constraints and inductive biases when applying machine learning to physics problems.