Optimal training of integer-valued neural networks with mixed integer programming

Recent work has shown potential in using Mixed Integer Programming (MIP) solvers to optimize certain aspects of neural networks (NNs). However the intriguing approach of training NNs with MIP solvers is under-explored. State-of-the-art-methods to train NNs are typically gradient-based and require si...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	PloS one Ročník 18; číslo 2; s. e0261029
Hlavní autoři:	Thorbjarnarson, Tómas, Yorke-Smith, Neil
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States Public Library of Science 01.02.2023 Public Library of Science (PLoS)
Témata:	Analysis Biology and Life Sciences Computer and Information Sciences Computer architecture Graphics processing units Integer programming Linear programming Mathematical models Medicine and Health Sciences Memory (Computers) Memory devices Mixed integer Network management systems Neural networks Neurons Optimization Parameters Physical Sciences Solvers Training Tuning Netherlands
ISSN:	1932-6203, 1932-6203
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!