Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Felipe Franca, M.Breternitz & Leandro Araujo (2019). Memory Efficient Weightless Neural Network using Bloom Filter. In 27 th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.
Exportar Referência (IEEE) 
F. M. França et al.,  "Memory Efficient Weightless Neural Network using Bloom Filter", in 27 th European Symp. on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2019
Exportar BibTeX 
@inproceedings{frança2019_1766220861682,
	author = "Felipe Franca and M.Breternitz and Leandro Araujo",
	title = "Memory Efficient Weightless Neural Network using Bloom Filter",
	booktitle = "27 th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",
	year = "2019",
	editor = "",
	volume = "",
	number = "",
	series = "",
	publisher = "",
	address = "",
	organization = "",
	url = "https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-83.pdf"
}
Exportar RIS 
TY  - CPAPER
TI  - Memory Efficient Weightless Neural Network using Bloom Filter
T2  - 27 th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
AU  - Felipe Franca
AU  - M.Breternitz
AU  - Leandro Araujo
PY  - 2019
SN  - 0000-0000
UR  - https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-83.pdf
AB  - Weightless Neural Networks are Artificial Neural Networks
based on RAM memory broadly explored as solution for pattern recog-
nition applications. Due to its memory approach, it can easily be im-
plemented in hardware and software providing efficient learning mecha-
nism. Unfortunately, the straightforward implementation requires a large
amount of memory resources making its adoption impracticable on mem-
ory constraint systems. In this paper, we propose a new model of Weight-
less Neural Network which utilizes Bloom Filters to implement RAM
nodes. By using Bloom Filters, the memory resources are widely re-
duced allowing false positives entries. The experiment results show that
our model using Bloom Filters achieves competitive accuracy, training
time and testing time, consuming up to 6 order of magnitude less mem-
ory resources in comparison with the standard Weightless Neural Network
model.
ER  -