Neuroevolution of Spiking Neural Networks Using Compositional Pattern Producing Networks
Spiking neural networks (SNNs) offer tremendous potential for the future of AI, including the ability to be implemented efficiently on neuromorphic systems. One of the challenges in building functioning SNNs is the training process, as standard error back-propagation cannot be easily applied. In this work, we extend an evolutionary approach for training SNNs by implementing an indirect encoding of individuals. Specifically, we evolve SNNs using Compositional Pattern Producing Networks, which are able to learn the connectivity patterns between neurons defined in a coordinate space. We validate the approach on multiple control and classification tasks.
- 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:
- 1649077
- Resource Relation:
- Conference: International Conference on Neuromorphic Systems (ICONS) - Oak Ridge, Tennessee, United States of America - 7/28/2020 8:00:00 AM-7/30/2020 8:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Multi-Objective Hyperparameter Optimization for Spiking Neural Network Neuroevolution
Energy Efficient Stochastic-Based Deep Spiking Neural Networks for Sparse Datasets
Training Spiking Neural Networks with Synaptic Plasticity under Integer Representation
Conference
·
Tue Jun 01 00:00:00 EDT 2021
·
OSTI ID:1649077
+3 more
Energy Efficient Stochastic-Based Deep Spiking Neural Networks for Sparse Datasets
Conference
·
Fri Dec 01 00:00:00 EST 2017
·
OSTI ID:1649077
Training Spiking Neural Networks with Synaptic Plasticity under Integer Representation
Conference
·
Thu Jul 01 00:00:00 EDT 2021
·
OSTI ID:1649077
+1 more