Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture

Catherine D. Schuman, Adam Disney and John Reynolds

Workshop on Machine Learning in HPC Environments, Supercomputing, Austin, TX, November, 2015.

PDF of the paper.

Abstract

Dynamic Adaptive Neural Network Array (DANNA) is a neuromorphic hardware implementation. It differs from most other neuromorphic projects in that it allows for programmability of structure, and it is trained or designed using evolutionary optimization. This paper describes the DANNA structure, how DANNA is trained using evolutionary optimization, and an application of DANNA to a very simple classification task.

Citation Information

Text: 
.inproceedings	sdr:15:d
author		C. D. Schuman and A. Disney and J. Reynolds
title		Dynamic Adaptive Neural Network Arrays: A Neuromorphic
		Architecture
booktitle	Workshop on Machine Learning in HPC Environments,
		Supercomputing
year		2015
address		Austin, TX
Bibtex: 
@INPROCEEDINGS{sdr:15:d,
  author = "C. D. Schuman and A. Disney and J. Reynolds",
  title = "Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture",
  booktitle = "Workshop on Machine Learning in HPC Environments, Supercomputing",
  year = "2015",
  address = "Austin, TX"
}