Paper Info
Title
Weightless Neural Networks as Memory Segmented Bloom Filters
Abstract
Weightless Neural Networks (WNNs) are Artificial Neural Networks based on RAM memory broadly explored as solution for pattern recognition applications. Memory-oriented solutions for pattern recognition are typically very simple, and can be easily implemented in hardware and software. Nonetheless, the straightforward implementation of a WNN requires a large amount of memory resources making its adoption impracticable on memory constrained systems. In this paper, we establish a foundational relationship between WNN and Bloom filters, presenting a novel unified framework which encompasses the two. In particular, we indicate that a WNN can be framed as a memory segmented Bloom filter. Leveraging such finding, we propose a new model of WNNs which utilizes Bloom filters to implement RAM nodes. Bloom filters reduce memory requirements, and allow false positives when determining if a given pattern was already seen in data. We experimentally found that for pattern recognition purposes such false positives can build robustness into the system. The experimental results show that our model using Bloom filters achieves competitive accuracy, training time and testing time, consuming up to 6 orders of magnitude less memory resources when compared against the standard Weightless Neural Network model.
Year
DOI
Venue
2020
10.1016/j.neucom.2020.01.115
Neurocomputing
Keywords
DocType
Volume
Weightless neural network,Bloom filter,Discriminator
Journal
416
ISSN
Citations 
PageRank 
0925-2312
2
0.38
References 
Authors
0
10
Name
Order
Citations
PageRank
Leandro Santiago120.38
Leticia Verona220.38
Fabio Rangel320.38
Fabrício Firmino420.38
Daniel Sadoc Menasché514423.47
Wouter Caarls6286.94
Mauricio Breternitz, Jr.7689.97
Sandip Kundu81103137.18
Priscila M. V. Lima910118.86
Felipe M. França10164.85