Home >

news Help

Publication Information


Title
Japanese: 
English:Low-Cost Reservoir Computing using Cellular Automata and Random Forests 
Author
Japanese: Ángel López García-Arias, 劉 載勲, Masanori Hashimoto.  
English: Ángel López García-Arias, Jaehoon Yu, Masanori Hashimoto.  
Language English 
Journal/Book name
Japanese: 
English: 
Volume, Number, Page         pp. 1-5
Published date Oct. 2020 
Publisher
Japanese: 
English: 
Conference name
Japanese: 
English:2020 IEEE International Symposium on Circuits and Systems (ISCAS) 
Conference site
Japanese: 
English: 
DOI https://doi.org/10.1109/ISCAS45731.2020.9180742
Abstract High-performance image classification models involve massive computation and an energy cost that are unaffordable for resource-limited platforms. As a solution, reservoir computing based on cellular automata has been proposed, but there is still room for improvement in terms of classification cost. This research builds on the previous work introducing enhancements at both the algorithmic and architectural level. Using a random forest classifier with binary features completely eliminates multiplication operations and 97% of addition operations. Also, memory usage can be decreased by pruning 82% of the least relevant augmented features. An architecture with an increased level of parallelism which processes images in a single pass reduces memory accesses, and reduces 60% of logic by optimizing FPGA mapping. These speed, power, and memory optimizations come at an accuracy tradeoff of a mere 0.6%

©2007 Tokyo Institute of Technology All rights reserved.