The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A computação de reservatórios (RC) é uma alternativa atraente aos modelos de aprendizado de máquina devido ao seu processo de treinamento computacionalmente barato e à simplicidade. Neste trabalho propomos EnsembleBloomCA, que utiliza autômatos celulares (CA) e um filtro Bloom conjunto para organizar um sistema RC. Em contraste com a maioria dos sistemas RC existentes, EnsembleBloomCA elimina todos os cálculos de ponto flutuante e multiplicação de inteiros. EnsembleBloomCA adota CA como reservatório no sistema RC porque pode ser implementado usando apenas operações binárias e, portanto, é energeticamente eficiente. A rica dinâmica de padrões criada pelo CA pode mapear a entrada original em um espaço de alta dimensão e fornecer mais recursos para o classificador. Utilizando um filtro Bloom conjunto como classificador, os recursos fornecidos pelo reservatório podem ser efetivamente memorizados. Nosso experimento revelou que a aplicação do mecanismo ensemble ao filtro Bloom resultou em uma redução significativa no custo de memória durante a fase de inferência. Em comparação com Bloom WiSARD, uma das obras de referência do estado da arte, o EnsembleBloomCA O modelo atinge uma redução de 43× no custo de memória, mantendo a mesma precisão. Nossa implementação de hardware também demonstrou que EnsembleBloomCA alcançou reduções de mais de 23× e 8.5× em área e potência, respectivamente.
Dehua LIANG
Osaka University
Jun SHIOMI
Osaka University
Noriyuki MIURA
Osaka University
Masanori HASHIMOTO
Kyoto University
Hiromitsu AWANO
Kyoto University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Dehua LIANG, Jun SHIOMI, Noriyuki MIURA, Masanori HASHIMOTO, Hiromitsu AWANO, "A Hardware Efficient Reservoir Computing System Using Cellular Automata and Ensemble Bloom Filter" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 7, pp. 1273-1282, July 2022, doi: 10.1587/transinf.2021EDP7203.
Abstract: Reservoir computing (RC) is an attractive alternative to machine learning models owing to its computationally inexpensive training process and simplicity. In this work, we propose EnsembleBloomCA, which utilizes cellular automata (CA) and an ensemble Bloom filter to organize an RC system. In contrast to most existing RC systems, EnsembleBloomCA eliminates all floating-point calculation and integer multiplication. EnsembleBloomCA adopts CA as the reservoir in the RC system because it can be implemented using only binary operations and is thus energy efficient. The rich pattern dynamics created by CA can map the original input into a high-dimensional space and provide more features for the classifier. Utilizing an ensemble Bloom filter as the classifier, the features provided by the reservoir can be effectively memorized. Our experiment revealed that applying the ensemble mechanism to the Bloom filter resulted in a significant reduction in memory cost during the inference phase. In comparison with Bloom WiSARD, one of the state-of-the-art reference work, the EnsembleBloomCA model achieves a 43× reduction in memory cost while maintaining the same accuracy. Our hardware implementation also demonstrated that EnsembleBloomCA achieved over 23× and 8.5× reductions in area and power, respectively.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDP7203/_p
Copiar
@ARTICLE{e105-d_7_1273,
author={Dehua LIANG, Jun SHIOMI, Noriyuki MIURA, Masanori HASHIMOTO, Hiromitsu AWANO, },
journal={IEICE TRANSACTIONS on Information},
title={A Hardware Efficient Reservoir Computing System Using Cellular Automata and Ensemble Bloom Filter},
year={2022},
volume={E105-D},
number={7},
pages={1273-1282},
abstract={Reservoir computing (RC) is an attractive alternative to machine learning models owing to its computationally inexpensive training process and simplicity. In this work, we propose EnsembleBloomCA, which utilizes cellular automata (CA) and an ensemble Bloom filter to organize an RC system. In contrast to most existing RC systems, EnsembleBloomCA eliminates all floating-point calculation and integer multiplication. EnsembleBloomCA adopts CA as the reservoir in the RC system because it can be implemented using only binary operations and is thus energy efficient. The rich pattern dynamics created by CA can map the original input into a high-dimensional space and provide more features for the classifier. Utilizing an ensemble Bloom filter as the classifier, the features provided by the reservoir can be effectively memorized. Our experiment revealed that applying the ensemble mechanism to the Bloom filter resulted in a significant reduction in memory cost during the inference phase. In comparison with Bloom WiSARD, one of the state-of-the-art reference work, the EnsembleBloomCA model achieves a 43× reduction in memory cost while maintaining the same accuracy. Our hardware implementation also demonstrated that EnsembleBloomCA achieved over 23× and 8.5× reductions in area and power, respectively.},
keywords={},
doi={10.1587/transinf.2021EDP7203},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - A Hardware Efficient Reservoir Computing System Using Cellular Automata and Ensemble Bloom Filter
T2 - IEICE TRANSACTIONS on Information
SP - 1273
EP - 1282
AU - Dehua LIANG
AU - Jun SHIOMI
AU - Noriyuki MIURA
AU - Masanori HASHIMOTO
AU - Hiromitsu AWANO
PY - 2022
DO - 10.1587/transinf.2021EDP7203
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2022
AB - Reservoir computing (RC) is an attractive alternative to machine learning models owing to its computationally inexpensive training process and simplicity. In this work, we propose EnsembleBloomCA, which utilizes cellular automata (CA) and an ensemble Bloom filter to organize an RC system. In contrast to most existing RC systems, EnsembleBloomCA eliminates all floating-point calculation and integer multiplication. EnsembleBloomCA adopts CA as the reservoir in the RC system because it can be implemented using only binary operations and is thus energy efficient. The rich pattern dynamics created by CA can map the original input into a high-dimensional space and provide more features for the classifier. Utilizing an ensemble Bloom filter as the classifier, the features provided by the reservoir can be effectively memorized. Our experiment revealed that applying the ensemble mechanism to the Bloom filter resulted in a significant reduction in memory cost during the inference phase. In comparison with Bloom WiSARD, one of the state-of-the-art reference work, the EnsembleBloomCA model achieves a 43× reduction in memory cost while maintaining the same accuracy. Our hardware implementation also demonstrated that EnsembleBloomCA achieved over 23× and 8.5× reductions in area and power, respectively.
ER -