Co-occurring keywords · papers mentioning both
Papers
Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks
NeurIPS 2024
StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
ICML 2024
Independent Component Alignment for Multi-Task Learning
CVPR 2023
Surprising Instabilities in Training Deep Networks and a Theoretical Analysis
NeurIPS 2022
Early Convolutions Help Transformers See Better
NeurIPS 2021
Explaining Knowledge Distillation by Quantifying the Knowledge
CVPR 2020