Skip navigation
Please use this identifier to cite or link to this item:
Title: Symbolic tensor differentiation for applications in machine learning
Authors: Zhabinski, A.
Zhabinskii, S.
Adzinets, Dz.
Keywords: публикации ученых
symbolic differentiation
machine learning
Einstein notation
Issue Date: 2017
Publisher: Croatian Society for Information and Communication Technology, Electronics and Microelectronics MIPRO, Croatia
Citation: Zhabinski, A. Symbolic tensor differentiation for applications in machine learning / A. Zhabinski, S. Zhabinskii, Dz. Adzinets // 40 Jubilee International Convention : proceedings (Мaу 22 -26, 2017, Croatia). - Croatia, 2017. – Рр. 338 – 1343. - DOI: 10.17223/1998863Х/34/18.
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.
Appears in Collections:Публикации в изданиях других стран

Files in This Item:
File Description SizeFormat 
Zhabinski_Symbolic.pdf873,13 kBAdobe PDFView/Open
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.