https://libeldoc.bsuir.by/handle/123456789/28423
Title: | Symbolic tensor differentiation for applications in machine learning |
Authors: | Zhabinski, A. Zhabinskii, S. Adzinets, D. N. |
Keywords: | публикации ученых;symbolic differentiation;machine learning;Einstein notation |
Issue Date: | 2017 |
Publisher: | Croatian Society for Information and Communication Technology |
Citation: | Zhabinski, A. Symbolic tensor differentiation for applications in machine learning / A. Zhabinski, S. Zhabinskii, Dz. Adzinets // 40 Jubilee International Convention : proceedings, Croatia, Мaу 22-26, 2017. – Croatia, 2017. – Р. 338–1343. |
Abstract: | Automated methods for computing derivatives of cost functions are essential to many modern applications of machine learning. Reverse-mode automatic differentiation provides relatively cheap means for it but generated code often requires a lot of memory and is hardly amenable to later optimizations. Symbolic differentiation, on the other hand, generates much more flexible code, yet applying it to multidimensional tensors is a poorly studied topic. In this paper presents a method for symbolic tensor differentiation based on extended Einstein indexing notation, which allows to overcome many limitation of both - automatic and classic symbolic differentiation, and generate efficient code for CPL and GPU. |
URI: | https://libeldoc.bsuir.by/handle/123456789/28423 |
DOI: | 10.17223/1998863Х/34/18 |
Appears in Collections: | Публикации в зарубежных изданиях |
File | Description | Size | Format | |
---|---|---|---|---|
Zhabinski_Symbolic.pdf | 873.13 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.