Please use this identifier to cite or link to this item:
http://hdl.handle.net/10071/26522
Author(s): | Susskind, Z. Bacellar, A. T. L. Arora, A. Villon, L. A. Q. Mendanha, R. Araújo, L. S. de. Dutra, D. L. C. Lima, P. M. V. França, F. M. G. Miranda, I. D. S. Breternitz Jr., M. John, L. K. |
Date: | 2022 |
Title: | Pruning weightless neural networks |
Book title/volume: | ESANN 2022 proceedings |
Pages: | 37 - 42 |
Event title: | 30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning |
Reference: | Susskind, Z., Bacellar, A. T. L., Arora, A., Villon, L. A. Q., Mendanha, R., Araújo, L. S. de., Dutra, D. L. C., Lima, P. M. V., França, F. M. G., Miranda, I. D. S., Breternitz Jr., M., & John, L. K. (2022). Pruning weightless neural networks. In ESANN 2022 proceedings (pp. 37-42). https://doi.org/10.14428/esann/2022.ES2022-55 |
ISBN: | 978287587084-1 |
DOI (Digital Object Identifier): | 10.14428/esann/2022.ES2022-55 |
Abstract: | Weightless neural networks (WNNs) are a type of machine learning model which perform prediction using lookup tables (LUTs) instead of arithmetic operations. Recent advancements in WNNs have reduced model sizes and improved accuracies, reducing the gap in accuracy with deep neural networks (DNNs). Modern DNNs leverage “pruning” techniques to reduce model size, but this has not previously been explored for WNNs. We propose a WNN pruning strategy based on identifying and culling the LUTs which contribute least to overall model accuracy. We demonstrate an average 40% reduction in model size with at most 1% reduction in accuracy. |
Peerreviewed: | yes |
Access type: | Open Access |
Appears in Collections: | ISTAR-CRI - Comunicações a conferências internacionais |
Files in This Item:
File | Size | Format | |
---|---|---|---|
conferenceobject_91315.pdf | 1,44 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.