Understanding Selection And Diversity For Evolution Of Spiking Recurrent Neural Networks
- ORNL
- University of Tennessee (UT)
Evolutionary optimization or genetic algorithms have been used to optimize a variety of neural network types, including spiking recurrent neural networks, and are attractive for many reasons. However, a key impediment to their widespread use is the potential for slow training times and failure to converge to a good fitness value in a reasonable amount of time. In this work, we evaluate the effect of different selection algorithms on the performance of an evolutionary optimization method for designing spiking recurrent neural networks, including those that are meant to be deployed in a neuromorphic system. We propose a selection approach that utilizes a richer understanding of the fitness of an individual network to inform the selection process and to promote diversity in the population. We show that including this feature can provide a significant increase in performance over utilizing a standard selection approach.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1479770
- Resource Relation:
- Conference: International Joint Conference on Neural Networks (IJCNN) - Rio de Janeiro, , Brazil - 7/8/2018 8:00:00 AM-7/13/2018 8:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks
Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training