Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization).

Zhenyu Zhu Fanghui Liu Grigorios G. Chrysos Volkan Cevher

Published in: CoRR (2022)

Keyphrases

deep learning
unsupervised learning
unsupervised feature learning
machine learning
deep architectures
restricted boltzmann machine
viewpoint
mental models
information retrieval
clustering algorithm
multiscale
information extraction
weakly supervised