Tensor-based Polynomial Features Generation for High-order Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F21%3A00353300" target="_blank" >RIV/68407700:21220/21:00353300 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/PC52310.2021.9447514" target="_blank" >https://doi.org/10.1109/PC52310.2021.9447514</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/PC52310.2021.9447514" target="_blank" >10.1109/PC52310.2021.9447514</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Tensor-based Polynomial Features Generation for High-order Neural Networks

Popis výsledku v původním jazyce

This paper discusses the methods and algorithms for polynomial features generation. The polynomial features generation is the very first step for the High-order Neural Units evaluation. The algorithms for polynomial features generation based on recursive calls are memory effective; however, these algorithms can not benefit from the modern hardware optimizations for neural networks focused on fast tensor operations on GPUs (Graphic Processing Units) and TPUs (Tensor Processing units). Moreover, the recursive calls with many operations are limiting for the application of automatic differentiation algorithms. That makes the design of a high order neural network with HONU in the later than the first hidden layer challenging. The tensor-based algorithm for polynomial features generation that tries to leverage TPU and GPU hardware architecture is introduced in this paper. The tensor-based algorithm's implementation is tested and compared with a straight-forward recursive algorithm and with SciKit-learn library implementation in Python programming language.

Název v anglickém jazyce

Tensor-based Polynomial Features Generation for High-order Neural Networks

Popis výsledku anglicky

This paper discusses the methods and algorithms for polynomial features generation. The polynomial features generation is the very first step for the High-order Neural Units evaluation. The algorithms for polynomial features generation based on recursive calls are memory effective; however, these algorithms can not benefit from the modern hardware optimizations for neural networks focused on fast tensor operations on GPUs (Graphic Processing Units) and TPUs (Tensor Processing units). Moreover, the recursive calls with many operations are limiting for the application of automatic differentiation algorithms. That makes the design of a high order neural network with HONU in the later than the first hidden layer challenging. The tensor-based algorithm for polynomial features generation that tries to leverage TPU and GPU hardware architecture is introduced in this paper. The tensor-based algorithm's implementation is tested and compared with a straight-forward recursive algorithm and with SciKit-learn library implementation in Python programming language.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF16_019%2F0000826" target="_blank" >EF16_019/0000826: Centrum pokročilých leteckých technologií</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 23rd International Conference on Process Control

ISBN

978-1-6654-0330-6

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

175-179

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Štrbské Pleso

Datum konání akce

1. 6. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000723653400030