Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Breternitz Jr, Mauricio"'
Autor:
Bacellar, Alan T. L., Susskind, Zachary, Breternitz Jr., Mauricio, John, Eugene, John, Lizy K., Lima, Priscila M. V., França, Felipe M. G.
Publikováno v:
International Conference on Machine Learning (ICML) 2024
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 L
Externí odkaz:
http://arxiv.org/abs/2410.11112
Autor:
Susskind, Zachary, Arora, Aman, Miranda, Igor D. S., Bacellar, Alan T. L., Villon, Luis A. Q., Katopodis, Rafael F., de Araujo, Leandro S., Dutra, Diego L. C., Lima, Priscila M. V., Franca, Felipe M. G., Breternitz Jr., Mauricio, John, Lizy K.
The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches to enabling deep neural networks (DNNs) in this domain, including pruni
Externí odkaz:
http://arxiv.org/abs/2304.10618
Autor:
Susskind, Zachary, Arora, Aman, Miranda, Igor Dantas Dos Santos, Villon, Luis Armando Quintanilla, Katopodis, Rafael Fontella, de Araujo, Leandro Santiago, Dutra, Diego Leonel Cadette, Lima, Priscila Machado Vieira, Franca, Felipe Maia Galvao, Breternitz Jr., Mauricio, John, Lizy K.
Weightless Neural Networks (WNNs) are a class of machine learning model which use table lookups to perform inference. This is in contrast with Deep Neural Networks (DNNs), which use multiply-accumulate operations. State-of-the-art WNN architectures h
Externí odkaz:
http://arxiv.org/abs/2203.01479
Some Deep Neural Networks (DNN) have what we call lanes, or they can be reorganized as such. Lanes are paths in the network which are data-independent and typically learn different features or add resilience to the network. Given their data-independe
Externí odkaz:
http://arxiv.org/abs/1908.03935
We introduce Multi-Lane Capsule Networks (MLCN), which are a separable and resource efficient organization of Capsule Networks (CapsNet) that allows parallel processing, while achieving high accuracy at reduced cost. A MLCN is composed of a number of
Externí odkaz:
http://arxiv.org/abs/1902.08431
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Santiago, Leandro, Verona, Leticia, Rangel, Fabio, Firmino, Fabrício, Menasché, Daniel S., Caarls, Wouter, Breternitz Jr, Mauricio, Kundu, Sandip, Lima, Priscila M.V., França, Felipe M.G.
Publikováno v:
In Neurocomputing 27 November 2020 416:292-304
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
International Conference on Hardware Software Codesign; Jan2005, p160-165, 6p