John J. M. Reynolds, James S. Plank, Catherine D. Schuman, Grant Bruer, Adam W. Disney, Mark Dean and Garrett S. Rose

July, 2018

ICONS: International Conference on Neuromorphic Systems

https://ornlcda.github.io/icons2018/

View Article

Abstract

A variety of neural network models and machine learning techniques have arisen over the past decade, and their successes with image classification have been stunning. With other classification tasks, selecting and configuring a neural network solution is not straightforward. In this paper, we evaluate and compare a variety of neural network models, trained by a variety of machine learning techniques, on a variety of classification tasks. While Deep Learning typically exhibits the best classification accuracy, we note the promise of Reservoir Computing, and evolutionary optimization on spiking neural networks. In many cases, these technologies perform as well as, or better than Deep Learning, and the resulting networks are much smaller than their Deep Learning counterparts.

Citation Information

Text

author          J. J. M. Reynolds and J. S. Plank and C. D. Schuman and G. Bruer and
                A. W. Disney and M. Dean and G. S. Rose
title           A Comparison of Neuromorphic Classification Tasks
booktitle       International Conference on Neuromorphic Computing Systems
publisher       ACM
address         Knoxville, TN
month           July
year            2018
doi             10.1145/3229884.3229896
where           https://dl.acm.org/citation.cfm?id=3229896

Bibtex

@INPROCEEDINGS{rps:18:acn,
    author = "J. J. M. Reynolds and J. S. Plank and C. D. Schuman and G. Bruer and
                A. W. Disney and M. Dean and G. S. Rose",
    title = "A Comparison of Neuromorphic Classification Tasks",
    booktitle = "International Conference on Neuromorphic Computing Systems",
    publisher = "ACM",
    address = "Knoxville, TN",
    month = "July",
    year = "2018",
    doi = "10.1145/3229884.3229896",
    where = "https://dl.acm.org/citation.cfm?id=3229896"
}