Catherine D. Schuman, J. Douglas Birdwell, and Mark E. Dean.

November, 2014

Procedia Computer Science, Elsevier, Volume 41.

http://www.sciencedirect.com/science/journal/18770509/41

View Article

Abstract

We discuss a neuroscience-inspired dynamic architecture (NIDA) and associated design method based on evolutionary optimization. NIDA networks designed to perform anomaly detection tasks and control tasks have been shown to be successful in previous work. In particular, NIDA networks perform well on tasks that have a temporal component. We present methods for using NIDA networks on classification tasks in which there is no temporal component, in particular, the handwritten digit classification task. The approach we use for both methods produces useful subnetworks that can be combined to produce a final network or combined to produce results using an ensemble method. We discuss how a similar approach can be applied to other problem types.

Citation Information

Text

author     C. D. Schuman and J. D. Birdwell and M. E. Dean
title      Spatiotemporal Classification Using Neuroscience-Inspired Dynamic Architectures
journal    Procedia Computer Science
publisher  Elsevier
volume     41
year       2014
pages      89-97
where      http://www.sciencedirect.com/science/article/pii/S1877050914015348

Bibtex

@ARTICLE{sbd:14:scu,
  author = "C. D. Schuman and J. D. Birdwell and M. E. Dean",
  title = "Spatiotemporal Classification Using Neuroscience-Inspired Dynamic Architectures",
  journal = "Procedia Computer Science",
  publisher = "Elsevier",
  volume = "41",
  year = "2014",
  pages = "89-97",
  where = "http://www.sciencedirect.com/science/article/pii/S1877050914015348"
}