Implementation Guidelines for Image Processing with Convolutional Neural Networks

Autor:	Florian Bordes, Erich Schikuta
Rok vydání:	2016
Předmět:	Speedup Artificial neural network Computer science business.industry Deep learning Fast Fourier transform Image processing computer.software_genre Convolutional neural network Domain (software engineering) Artificial intelligence Data mining Focus (optics) business computer
Zdroj:	MoMM University of Vienna-u:cris
DOI:	10.1145/3007120.3007165
Popis:	The domain of image processing technologies comprises many methods and algorithms for the analysis of signals, representing data sets, as photos or videos. In this paper we present a discussion and analysis, on the one hand, of classical image processing methods, as Fourier transformation, and, on the other hand, of neural networks. Specifically we focus on multi-layer and convolutional neural networks and give guidelines how images can be analyzed effectively and efficiently. To speed up the performance we identify various parallel software and hardware environments and evaluate, how parallelism can be used to improve performance of neural network operations. Based on our findings we derive several guidelines for applying different parallelization approaches on various sequential and parallel hardware infrastructure.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::701480b7c910e8e4ecfd9c29a874a427 https://doi.org/10.1145/3007120.3007165 Zobrazit plný text záznamu