TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Acceleration Approaches for Big Data Analysis

Tutkimustuotosvertaisarvioitu

Standard

Acceleration Approaches for Big Data Analysis. / Muravev, Anton; Thanh Tran, Dat; Iosifidis, Alexandros; Kiranyaz, Serkan; Gabbouj, Moncef.

2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018.

Tutkimustuotosvertaisarvioitu

Harvard

Muravev, A, Thanh Tran, D, Iosifidis, A, Kiranyaz, S & Gabbouj, M 2018, Acceleration Approaches for Big Data Analysis. julkaisussa 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 7/10/18. https://doi.org/10.1109/ICIP.2018.8451082

APA

Muravev, A., Thanh Tran, D., Iosifidis, A., Kiranyaz, S., & Gabbouj, M. (2018). Acceleration Approaches for Big Data Analysis. teoksessa 2018 25th IEEE International Conference on Image Processing (ICIP) IEEE. https://doi.org/10.1109/ICIP.2018.8451082

Vancouver

Muravev A, Thanh Tran D, Iosifidis A, Kiranyaz S, Gabbouj M. Acceleration Approaches for Big Data Analysis. julkaisussa 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE. 2018 https://doi.org/10.1109/ICIP.2018.8451082

Author

Muravev, Anton ; Thanh Tran, Dat ; Iosifidis, Alexandros ; Kiranyaz, Serkan ; Gabbouj, Moncef. / Acceleration Approaches for Big Data Analysis. 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018.

Bibtex - Lataa

@inproceedings{8bb04e76c2dc40ad995ac9dbf6c74220,
title = "Acceleration Approaches for Big Data Analysis",
abstract = "The massive size of data that needs to be processed by Machine Learning models nowadays sets new challenges related to their computational complexity and memory footprint. These challenges span all processing steps involved in the application of the related models, i.e., from the fundamental processing steps needed to evaluate distances of vectors, to the optimization of large-scale systems, e.g. for non-linear regression using kernels, or the speed up of deep learning models formed by billions of parameters. In order to address these challenges, new approximate solutions have been recently proposed based on matrix/tensor decompositions, randomization and quantization strategies. This paper provides a comprehensive review of the related methodologies and discusses their connections.",
author = "Anton Muravev and {Thanh Tran}, Dat and Alexandros Iosifidis and Serkan Kiranyaz and Moncef Gabbouj",
note = "jufoid=57423 EXT={"}Kiranyaz, Serkan{"} INT=sgn,{"}Thanh Tran, Dat{"}",
year = "2018",
month = "9",
day = "6",
doi = "10.1109/ICIP.2018.8451082",
language = "English",
publisher = "IEEE",
booktitle = "2018 25th IEEE International Conference on Image Processing (ICIP)",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Acceleration Approaches for Big Data Analysis

AU - Muravev, Anton

AU - Thanh Tran, Dat

AU - Iosifidis, Alexandros

AU - Kiranyaz, Serkan

AU - Gabbouj, Moncef

N1 - jufoid=57423 EXT="Kiranyaz, Serkan" INT=sgn,"Thanh Tran, Dat"

PY - 2018/9/6

Y1 - 2018/9/6

N2 - The massive size of data that needs to be processed by Machine Learning models nowadays sets new challenges related to their computational complexity and memory footprint. These challenges span all processing steps involved in the application of the related models, i.e., from the fundamental processing steps needed to evaluate distances of vectors, to the optimization of large-scale systems, e.g. for non-linear regression using kernels, or the speed up of deep learning models formed by billions of parameters. In order to address these challenges, new approximate solutions have been recently proposed based on matrix/tensor decompositions, randomization and quantization strategies. This paper provides a comprehensive review of the related methodologies and discusses their connections.

AB - The massive size of data that needs to be processed by Machine Learning models nowadays sets new challenges related to their computational complexity and memory footprint. These challenges span all processing steps involved in the application of the related models, i.e., from the fundamental processing steps needed to evaluate distances of vectors, to the optimization of large-scale systems, e.g. for non-linear regression using kernels, or the speed up of deep learning models formed by billions of parameters. In order to address these challenges, new approximate solutions have been recently proposed based on matrix/tensor decompositions, randomization and quantization strategies. This paper provides a comprehensive review of the related methodologies and discusses their connections.

U2 - 10.1109/ICIP.2018.8451082

DO - 10.1109/ICIP.2018.8451082

M3 - Conference contribution

BT - 2018 25th IEEE International Conference on Image Processing (ICIP)

PB - IEEE

ER -