Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks
- University of Minnesota
- ORNL
Inspired by the connectivity mechanisms in the brain, neuromorphic computing architectures model Spiking Neural Networks (SNNs) in silicon. As such, neuromorphic architectures are designed and developed with the goal of having small, low power chips that can perform control and machine learning tasks. However, the power consumption of the developed hardware can greatly depend on the size of the network that is being evaluated on the chip. Furthermore, the accuracy of a trained SNN that is evaluated on chip can change due to voltage and current variations in the hardware that perturb the learned weights of the network. While efforts are made on the hardware side to minimize those perturbations, a software based strategy to make the deployed networks more resilient can help further alleviate that issue. In this work, we study Spiking Neural Networks in two neuromorphic architecture implementations with the goal of decreasing their size, while at the same time increasing their resiliency to hardware faults. We leverage an evolutionary algorithm to train the SNNs and propose a multiobjective fitness function to optimize the size and resiliency of the SNN. We demonstrate that this strategy leads to well-performing, small-sized networks that are more resilient to hardware faults.
- 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:
- 1606935
- Resource Relation:
- Conference: IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) - New York, New York, United States of America - 10/10/2019 8:00:00 AM-10/12/2019 8:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Benchmarking the Performance of Neuromorphic and Spiking Neural Network Simulators
Multi-Objective Hyperparameter Optimization for Spiking Neural Network Neuroevolution