%0 Conference Proceedings
%T Large datasets: a mixed method to adapt and improve their learning by neural networks used in regression contexts
%+ Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies (UMR 6174) (FEMTO-ST)
%+ Algorithms for the Grid (ALGORILLE)
%A Sauget, Marc
%A Henriet, Julien
%A Salomon, Michel
%A Contassot-Vivier, Sylvain
%Z Part 9: Machine Learning
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI)
%C Corfu, Greece
%Y Lazaros Iliadis
%Y Chrisina Jayne
%I Springer
%3 Engineering Applications of Neural Networks
%V AICT-363
%N Part I
%P 182-191
%8 2011-09-15
%D 2011
%R 10.1007/978-3-642-23957-1_21
%K Pre-clinical studies
%K Doses Distributions
%K Neural Networks
%K Learning algorithms
%K External radiotherapy
%K Data extraction
%Z Computer Science [cs]
%Z Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]Conference papers
%X The purpose of this work is to further study the relevance of accelerating the Monte-Carlo calculations for the gamma rays external radiotherapy through feed-forward neural networks. We have previously presented a parallel incremental algorithm that builds neural networks of reduced size, while providing high quality approximations of the dose deposit~\cite{Vecpar08b}. Our parallel algorithm consists in an optimized decomposition of the initial learning dataset (also called learning domain) in as much subsets as available processors. However, although that decomposition provides subsets of similar signal complexities, their sizes may be quite different, still implying potential differences in their learning times. This paper presents an efficient data extraction allowing a good and balanced training without any loss of signal information. As will be shown, the resulting irregular decomposition permits an important improvement in the learning time of the global network.
%G English
%Z TC 12
%Z WG 12.5
%2 https://inria.hal.science/hal-00643870/document
%2 https://inria.hal.science/hal-00643870/file/978-3-642-23957-1_21_Chapter.pdf
%L hal-00643870
%U https://inria.hal.science/hal-00643870
%~ CNRS
%~ INRIA
%~ UNIV-FCOMTE
%~ UNIV-BM
%~ ENSMM
%~ INPL
%~ FEMTO-ST
%~ INRIA-LORRAINE
%~ LORIA2
%~ UNIV-BM-THESE
%~ INRIA-NANCY-GRAND-EST
%~ TESTALAIN1
%~ IFIP
%~ IFIP-AICT
%~ UNIV-LORRAINE
%~ INRIA2
%~ IFIP-TC
%~ IFIP-WG
%~ IFIP-TC12
%~ LORIA
%~ IFIP-AIAI
%~ IFIP-WG12-5
%~ IFIP-AICT-363
%~ IFIP-EANN