Resilience and Robustness of Spiking Neural Networks for Neuromorphic Systems
- ORNL
- Purdue University
Though robustness and resilience are commonly quoted as features of neuromorphic computing systems, the expected performance of neuromorphic systems in the face of hardware failures is not clear. In this work, we study the effect of failures on the performance of four different training algo-rithms for spiking neural networks on neuromorphic systems: two back-propagation-based training approaches (Whetstone and SLAYER), a liquid state machine or reservoir computing approach, and an evolutionary optimization-based approach (EONS). We show that these four different approaches have very different resilience characteristics with respect to simulated hardware failures. We then analyze an approach for training more resilient spiking neural networks using the evolutionary optimization approach. We show how this approach produces more resilient networks and discuss how it can be extended to other spiking neural network training approaches as well.
- 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:
- 1671419
- Resource Relation:
- Conference: International Joint Conference on Neural Networks (IJCNN) - Glasgow, , Scotland - 7/19/2020 8:00:00 AM-7/24/2020 8:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
A Software Framework for Comparing Training Approaches for Spiking Neuromorphic Systems
Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks