Autor:	Turner, Jack, Crowley, Elliot J., O'Boyle, Michael F.P.
Předmět:	ARTIFICIAL neural networks SYSTEMS design PROGRAM transformation MATHEMATICAL convolutions CONVOLUTIONAL neural networks DEEP learning
Zdroj:	Communications of the ACM; Oct2024, Vol. 67 Issue 10, p92-100, 9p
Abstrakt:	This article presents a unification of previously separate actions--design and optimization--into neural architecture search (NAS) as program transformation exploration for deep neural network performance improvement. The article provides an overview of different types of convolution and transformations and how NAS operations can be expressed as transformation. This research introduces a new safety metric based on Fisher Potential and ultimately the unified framework is tested in TVM, an open source deep learning compiler.
Databáze:	Complementary Index
Externí odkaz:	Zobrazit plný text záznamu