Home > Research > Publications & Outputs > Stochastic Computing co-processing elements for...

Research

Associated organisational units

Links

Text available via DOI:

View graph of relations

Stochastic Computing co-processing elements for Evolving Autonomous Data Partitioning

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Stochastic Computing co-processing elements for Evolving Autonomous Data Partitioning. / Moran, Alejandro; Canals, Vincent; Angelov, Plamen P. et al.
36th Conference on Design of Circuits and Integrated Systems, DCIS 2021. IEEE, 2021. p. 1-6 (36th Conference on Design of Circuits and Integrated Systems, DCIS 2021).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Moran, A, Canals, V, Angelov, PP, Frasser, CF, Skibinsky-Gitlin, ES, Font, J, Isern, E, Roca, M & Rossello, JL 2021, Stochastic Computing co-processing elements for Evolving Autonomous Data Partitioning. in 36th Conference on Design of Circuits and Integrated Systems, DCIS 2021. 36th Conference on Design of Circuits and Integrated Systems, DCIS 2021, IEEE, pp. 1-6. https://doi.org/10.1109/dcis53048.2021.9666167

APA

Moran, A., Canals, V., Angelov, P. P., Frasser, C. F., Skibinsky-Gitlin, E. S., Font, J., Isern, E., Roca, M., & Rossello, J. L. (2021). Stochastic Computing co-processing elements for Evolving Autonomous Data Partitioning. In 36th Conference on Design of Circuits and Integrated Systems, DCIS 2021 (pp. 1-6). (36th Conference on Design of Circuits and Integrated Systems, DCIS 2021). IEEE. https://doi.org/10.1109/dcis53048.2021.9666167

Vancouver

Moran A, Canals V, Angelov PP, Frasser CF, Skibinsky-Gitlin ES, Font J et al. Stochastic Computing co-processing elements for Evolving Autonomous Data Partitioning. In 36th Conference on Design of Circuits and Integrated Systems, DCIS 2021. IEEE. 2021. p. 1-6. (36th Conference on Design of Circuits and Integrated Systems, DCIS 2021). doi: 10.1109/dcis53048.2021.9666167

Author

Moran, Alejandro ; Canals, Vincent ; Angelov, Plamen P. et al. / Stochastic Computing co-processing elements for Evolving Autonomous Data Partitioning. 36th Conference on Design of Circuits and Integrated Systems, DCIS 2021. IEEE, 2021. pp. 1-6 (36th Conference on Design of Circuits and Integrated Systems, DCIS 2021).

Bibtex

@inproceedings{f00a38b6c2aa4d9393150babcf7580b5,
title = "Stochastic Computing co-processing elements for Evolving Autonomous Data Partitioning",
abstract = "This paper proposes a hardware acceleration of a recently proposed evolving Autonomous Data Partitioning (ADP) algorithm by an unconventional computational technique as stochastic computing. The ADP algorithm is non-parametric and its evolving version creates data clouds from streaming data samples. Since the ADP algorithm calculates maximum and minimum Euclidean norms, distances and maximum/minimum arguments, proper hardware acceleration based on the Stochastic Computing design should reduce power consumption by degrading arithmetic precision in the future embedded system. The simulations of the 8-bit proposed design for different datasets show more or less impact on the clustering metrics due to arithmetic inaccuracies compared to the results obtained by the equivalent floating-point design. Despite these differences, in certain circumstances the Stochastic Computing design can outperform the floating-point design. In fact, the clustering quality metrics results obtained for different datasets are quite similar (or slightly inferior in some tests) to the results of evolving ADP original paper, in which all calculations were performed in floating-point precision.",
author = "Alejandro Moran and Vincent Canals and Angelov, {Plamen P.} and Frasser, {Christian F.} and Skibinsky-Gitlin, {Erik S.} and Joan Font and Eugeni Isern and Miquel Roca and Rossello, {Josep L.}",
year = "2021",
month = nov,
day = "24",
doi = "10.1109/dcis53048.2021.9666167",
language = "English",
series = "36th Conference on Design of Circuits and Integrated Systems, DCIS 2021",
publisher = "IEEE",
pages = "1--6",
booktitle = "36th Conference on Design of Circuits and Integrated Systems, DCIS 2021",

}

RIS

TY - GEN

T1 - Stochastic Computing co-processing elements for Evolving Autonomous Data Partitioning

AU - Moran, Alejandro

AU - Canals, Vincent

AU - Angelov, Plamen P.

AU - Frasser, Christian F.

AU - Skibinsky-Gitlin, Erik S.

AU - Font, Joan

AU - Isern, Eugeni

AU - Roca, Miquel

AU - Rossello, Josep L.

PY - 2021/11/24

Y1 - 2021/11/24

N2 - This paper proposes a hardware acceleration of a recently proposed evolving Autonomous Data Partitioning (ADP) algorithm by an unconventional computational technique as stochastic computing. The ADP algorithm is non-parametric and its evolving version creates data clouds from streaming data samples. Since the ADP algorithm calculates maximum and minimum Euclidean norms, distances and maximum/minimum arguments, proper hardware acceleration based on the Stochastic Computing design should reduce power consumption by degrading arithmetic precision in the future embedded system. The simulations of the 8-bit proposed design for different datasets show more or less impact on the clustering metrics due to arithmetic inaccuracies compared to the results obtained by the equivalent floating-point design. Despite these differences, in certain circumstances the Stochastic Computing design can outperform the floating-point design. In fact, the clustering quality metrics results obtained for different datasets are quite similar (or slightly inferior in some tests) to the results of evolving ADP original paper, in which all calculations were performed in floating-point precision.

AB - This paper proposes a hardware acceleration of a recently proposed evolving Autonomous Data Partitioning (ADP) algorithm by an unconventional computational technique as stochastic computing. The ADP algorithm is non-parametric and its evolving version creates data clouds from streaming data samples. Since the ADP algorithm calculates maximum and minimum Euclidean norms, distances and maximum/minimum arguments, proper hardware acceleration based on the Stochastic Computing design should reduce power consumption by degrading arithmetic precision in the future embedded system. The simulations of the 8-bit proposed design for different datasets show more or less impact on the clustering metrics due to arithmetic inaccuracies compared to the results obtained by the equivalent floating-point design. Despite these differences, in certain circumstances the Stochastic Computing design can outperform the floating-point design. In fact, the clustering quality metrics results obtained for different datasets are quite similar (or slightly inferior in some tests) to the results of evolving ADP original paper, in which all calculations were performed in floating-point precision.

U2 - 10.1109/dcis53048.2021.9666167

DO - 10.1109/dcis53048.2021.9666167

M3 - Conference contribution/Paper

T3 - 36th Conference on Design of Circuits and Integrated Systems, DCIS 2021

SP - 1

EP - 6

BT - 36th Conference on Design of Circuits and Integrated Systems, DCIS 2021

PB - IEEE

ER -