Parallel Evolutionary Optimization for Neuromorphic Network Training
- ORNL
- University of Tennessee (UT)
- North Carolina State University (NCSU), Raleigh
One of the key impediments to the success of current neuromorphic computing architectures is the issue of how best to program them. Evolutionary optimization (EO) is one promising programming technique; in particular, its wide applicability makes it especially attractive for neuromorphic architectures, which can have many different characteristics. In this paper, we explore different facets of EO on a spiking neuromorphic computing model called DANNA. We focus on the performance of EO in the design of our DANNA simulator, and on how to structure EO on both multicore and massively parallel computing systems. We evaluate how our parallel methods impact the performance of EO on Titan, the U.S.'s largest open science supercomputer, and BOB, a Beowulf-style cluster of Raspberry Pi's. We also focus on how to improve the EO by evaluating commonality in higher performing neural networks, and present the result of a study that evaluates the EO performed by Titan.
- Research Organization:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF)
- Sponsoring Organization:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1335354
- Resource Relation:
- Conference: Machine Learning in HPC Environments Worshop (Held in conjunction with SC16), Salt Lake City, UT, USA, 20161114, 20161114
- Country of Publication:
- United States
- Language:
- English
Similar Records
NeoN: Neuromorphic Control for Autonomous Robotic Navigation
Benchmarking the Performance of Neuromorphic and Spiking Neural Network Simulators