Exportar Publicação

M.Breternitz, Felipe Franca & Priscila Lima (2022). Weightless Neural Networks - a lightweight approach for efficient Machine Learning. Seminar Series - CMM Center for Mathematical Morphology- Paris Tech.

M. B. Jr. et al.,  "Weightless Neural Networks - a lightweight approach for efficient Machine Learning", in Seminar Series - CMM Center for Mathematical Morphology- Paris Tech, online, 2022

@misc{jr.2022_1765591899784,
	author = "M.Breternitz and Felipe Franca and Priscila Lima",
	title = "Weightless Neural Networks - a lightweight approach for efficient Machine Learning",
	year = "2022",
	howpublished = "Ambos (impresso e digital)",
	url = "https://interne.cmm.minesparis.psl.eu/wiki/doku.php/seminaires/start"
}

TY  - CPAPER
TI  - Weightless Neural Networks - a lightweight approach for efficient Machine Learning
T2  - Seminar Series - CMM Center for Mathematical Morphology- Paris Tech
AU  - M.Breternitz
AU  - Felipe Franca
AU  - Priscila Lima
PY  - 2022
CY  - online
UR  - https://interne.cmm.minesparis.psl.eu/wiki/doku.php/seminaires/start
AB  - Weightless neural networks (WNNs) are a type of neural model
which use random access memory (RAM) to determine neuron activation, as opposed to weights and dot products commonly used in modern deep learning approaches. This makes WNN attractive for a class of applications wherein the computational load (and energy requirements) is limited due to device size, cost or battery lifetimes. Furthermore, WNN have a large VC dimension, indicating that the lowered costs do not imply in a reduction of classification ability. The Vapnik–Chervonenkis (VC) dimension measures the complexity of the knowledge represented by a set of functions that can be
encoded by a binary classification algorithm. Previous work demonstrates that the VC dimension of WiSARD is very
large indicating a large capacity for discrimination at reduced resource costs.

ER  -