Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/34358
Autoria: | Bacellar, A. Susskind, Z. Breternitz Jr., M. John, E. John, L. Lima, P. França, F. |
Editor: | Salakhutdinov R., Kolter Z., Heller K., Weller A., Oliver N., Scarlett J., Berkenkamp F. |
Data: | 2024 |
Título próprio: | Differentiable weightless neural networks |
Volume: | 235 |
Título e volume do livro: | Proceedings of the 41st International Conference on Machine Learning, PMLR |
Paginação: | 2277 - 2295 |
Título do evento: | Proceedings of Machine Learning Research |
Referência bibliográfica: | Bacellar, A., Susskind, Z., Breternitz Jr., M., John, E., John, L., Lima, P., & França, F. (2024). Differentiable weightless neural networks. In R. Salakhutdinov, Z. Kolter, K. Heller, A. Weller, N. Oliver, J. Scarlett, & F. Berkenkamp (Eds.), Proceedings of the 41st International Conference on Machine Learning, PMLR (pp. 2277-2295). ML Research Press. http://hdl.handle.net/10071/34358 |
ISSN: | 2640-3498 |
Palavras-chave: | Machine learning Differentiable networks Weightless neural networks |
Resumo: | We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference technique for approximate differentiation of binary values. We propose Learnable Mapping, Learnable Reduction, and Spectral Regularization to further improve the accuracy and efficiency of these models. We evaluate DWNs in three edge computing contexts: (1) an FPGA-based hardware accelerator, where they demonstrate superior latency, throughput, energy efficiency, and model area compared to state-of-the-art solutions, (2) a low-power microcontroller, where they achieve preferable accuracy to XGBoost while subject to stringent memory constraints, and (3) ultralow-cost chips, where they consistently outperform small models in both accuracy and projected hardware area. DWNs also compare favorably against leading approaches for tabular datasets, with higher average rank. Overall, our work positions DWNs as a pioneering solution for edge-compatible high-throughput neural networks. |
Arbitragem científica: | yes |
Acesso: | Acesso Aberto |
Aparece nas coleções: | ISTAR-CRI - Comunicações a conferências internacionais |
Ficheiros deste registo:
Ficheiro | Tamanho | Formato | |
---|---|---|---|
conferenceObject_105156.pdf | 1,66 MB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.