Exportar Publicação

Miranda, I. D. S., Arora, A., Susskind, Z., Souza, J. S. A., Jadhao, M. P., Villon, L. A. Q....John, L. K. (2023). COIN: Combinational Intelligent Networks. In Cardoso, J. M. P., Jimborean, A., and Mentens, N. (Ed.), 2023 IEEE 34th International Conference on Application-specific Systems, Architectures and Processors (ASAP). Porto, Portugal: IEEE.

I. Miranda et al.,  "COIN: Combinational Intelligent Networks", in 2023 IEEE 34th Int. Conf. on Application-specific Systems, Architectures and Processors (ASAP), Cardoso, J. M. P., Jimborean, A., and Mentens, N., Ed., Porto, Portugal, IEEE, 2023

@inproceedings{miranda2023_1775076248427,
	author = "Miranda, I. D. S. and Arora, A. and Susskind, Z. and Souza, J. S. A. and Jadhao, M. P. and Villon, L. A. Q. and Dutra, D. L. C. and Lima, P. M. V. and França, F. M. G. and Breternitz Jr., M. and John, L. K.",
	title = "COIN: Combinational Intelligent Networks",
	booktitle = "2023 IEEE 34th International Conference on Application-specific Systems, Architectures and Processors (ASAP)",
	year = "2023",
	editor = "Cardoso, J. M. P., Jimborean, A., and Mentens, N.",
	volume = "",
	number = "",
	series = "",
	doi = "10.1109/ASAP57973.2023.00016",
	publisher = "IEEE",
	address = "Porto, Portugal",
	organization = "",
	url = "https://ieeexplore.ieee.org/xpl/conhome/10265289/proceeding"
}

TY  - CPAPER
TI  - COIN: Combinational Intelligent Networks
T2  - 2023 IEEE 34th International Conference on Application-specific Systems, Architectures and Processors (ASAP)
AU  - Miranda, I. D. S.
AU  - Arora, A.
AU  - Susskind, Z.
AU  - Souza, J. S. A.
AU  - Jadhao, M. P.
AU  - Villon, L. A. Q.
AU  - Dutra, D. L. C.
AU  - Lima, P. M. V.
AU  - França, F. M. G.
AU  - Breternitz Jr., M.
AU  - John, L. K.
PY  - 2023
SN  - 2160-0511
DO  - 10.1109/ASAP57973.2023.00016
CY  - Porto, Portugal
UR  - https://ieeexplore.ieee.org/xpl/conhome/10265289/proceeding
AB  - We introduce Combinational Intelligent Networks (COIN), a machine learning technique that targets edge inference using low-resourced FPGAs or ASICs. COIN is an improvement on LogicWiSARD, a recent weightless neural network that achieves low power, small area, and high throughput. We convert the LogicWiSARD model into a binary neural network, train it using backpropagation, and then convert it to a COIN model. As a result, COIN can achieve higher accuracy than LogicWiSARD or it can require significantly fewer hardware resources when comparing models with similar accuracies. In comparison to a BNN implementation, FINN, small and large COIN models are more energy efficient demonstrating up to 11.5x higher inferences/Joule at similar accuracy. Our tool executes the complete flow, from training to RTL. and is publicly available.
ER  -