Island model for parallel evolutionary optimization of spiking neuromorphic computing
- ORNL
- 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
DANNA 2: Dynamic Adaptive Neural Network Arrays
|
conference | January 2018 |
Neuroevolution: from architectures to learning
|
journal | January 2008 |
The TENNLab Exploratory Neuromorphic Computing Framework
|
journal | July 2018 |
Distributed evolutionary algorithms and their models: A survey of the state-of-the-art
|
journal | September 2015 |
Similar Records
Benchmarking the Performance of Neuromorphic and Spiking Neural Network Simulators
DFSynthesizer: Dataflow-based Synthesis of Spiking Neural Networks to Neuromorphic Hardware
Bayesian-based Hyperparameter Optimization for Spiking Neuromorphic Systems
Journal Article
·
Thu Mar 18 00:00:00 EDT 2021
· Neurocomputing
·
OSTI ID:1546518
+1 more
DFSynthesizer: Dataflow-based Synthesis of Spiking Neural Networks to Neuromorphic Hardware
Journal Article
·
Sat May 28 00:00:00 EDT 2022
· ACM Transactions on Embedded Computing Systems
·
OSTI ID:1546518
+3 more
Bayesian-based Hyperparameter Optimization for Spiking Neuromorphic Systems
Conference
·
Sun Dec 01 00:00:00 EST 2019
·
OSTI ID:1546518
+3 more