Silhouette: Toward Performance-Conscious and Transferable CPU Embeddings

Autor:	Papon, Tarikul Islam, Wasay, Abdul
Rok vydání:	2022
Předmět:	Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Learned embeddings are widely used to obtain concise data representation and enable transfer learning between different data sets and tasks. In this paper, we present Silhouette, our approach that leverages publicly-available performance data sets to learn CPU embeddings. We show how these embeddings enable transfer learning between data sets of different types and sizes. Each of these scenarios leads to an improvement in accuracy for the target data set.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.08046 Zobrazit plný text záznamu View this record from Arxiv