Statistical Learning
cdda0657a9f32bc7ddd4343686e7371e-Paper-Conference.pdf
The optimization phase in deep learning consists in minimizing an objective function w.r.t. the set of
Learning Human Action Recognition Representations Without Real Humans
Existing work has attempted to alleviate these problems by blurring faces, downsampling videos, or training on synthetic data. On the other hand, analysis on the transferability of privacy-preserving pre-trained models to downstream tasks has been limited.
On the spectral bias of two-layer linear networks
The most forceful driver of advancements in the field of Machine Learning over the past decades has been the success of deep neural networks.