Island model for parallel evolutionary optimization of spiking neuromorphic computing

Conference · Mon Jul 01 00:00:00 EDT 2019

DOI:https://doi.org/10.1145/3319619.3322016· OSTI ID:1546518

Schuman, Catherine  ^[1]; Plank, James ^[2]; Patton, Robert  ^[1]; Potok, Thomas  ^[1]

---

1. ORNL
2. University of Tennessee (UT)

Parallel genetic algorithms (PGAs) can be used to accelerate optimization by exploiting large-scale computational resources. In this work, we describe a PGA framework for evolving spiking neural networks (SNNs) for neuromorphic hardware implementation. The PGA framework is based on an islands model with migration. We show that using this framework, better SNNs for neuromorphic systems can be evolved faster.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1546518
• Resource Relation: Conference: The Genetic and Evolutionary Computation Conference (GECCO 2019) - Prague, , Czech Republic - 7/13/2019 8:00:00 AM-7/17/2019 8:00:00 AM
• Country of Publication: United States
• Language: English