February 2016

Conference Paper

Dynamic Adaptive Neural Network Arrays: A Neuromorphic Architecture

By:
Schuman, Catherine D; Disney, Adam; Reynolds, John
Publication Date:
February 10, 2016
Conference Name:
Supercomputing 2015: Machine Learning in HPC Environment Workshop
Conference Location:
Austin, Texas, United States of America
View DOI Listing:
https://doi.org/10.1145/2834892.2834895

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.