Web: http://arxiv.org/abs/2201.11939

Jan. 31, 2022, 2:11 a.m. | James Wang, Cheng-Lin Yang

cs.LG updates on arXiv.org arxiv.org

Generalization of deep neural networks remains one of the main open problems
in machine learning. Previous theoretical works focused on deriving tight
bounds of model complexity, while empirical works revealed that neural networks
exhibit double descent with respect to both training sample counts and the
neural network size. In this paper, we empirically examined how different
layers of neural networks contribute differently to the model; we found that
early layers generally learn representations relevant to performance on both
training data …

arxiv model performance perspective

More from arxiv.org / cs.LG updates on arXiv.org

Senior Data Engineer

@ DAZN | Hammersmith, London, United Kingdom

Sr. Data Engineer, Growth

@ Netflix | Remote, United States

Data Engineer - Remote

@ Craft | Wrocław, Lower Silesian Voivodeship, Poland

Manager, Operations Data Science

@ Binance.US | Vancouver

Senior Machine Learning Researcher for Copilot

@ GitHub | Remote - Europe

Sr. Marketing Data Analyst

@ HoneyBook | San Francisco, CA