Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Harang, Rich"'
Autor:
Harang, Rich, Sanders, Hillary
A large obstacle to deploying deep learning models in practice is the process of updating models post-deployment (ideally, frequently). Deep neural networks can cost many thousands of dollars to train. When new data comes in the pipeline, you can tra
Externí odkaz:
http://arxiv.org/abs/2306.10181
Autor:
Harang, Rich, Sanders, Hillary
This paper concerns itself with the task of taking a large trained neural network and 'compressing' it to be smaller by deleting parameters or entire neurons, with minimal decreases in the resulting model accuracy. We compare various methods of param
Externí odkaz:
http://arxiv.org/abs/2306.10177
Autor:
An, Sungwon, Harang, Rich, Meeker, Kirsten, Granados-Fuentes, Daniel, Tsai, Connie A., Mazuski, Cristina, Kim, Jihee, Doyle, Francis J., Petzold, Linda R., Herzog, Erik D.
Publikováno v:
Proceedings of the National Academy of Sciences of the United States of America, 2013 Nov 01. 110(46), 18358-18358.
Externí odkaz:
https://www.jstor.org/stable/23757543
