Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks
This work addresses power and reliability issues in neuromorphic computing for low-power machine learning applications, but it is incremental as it builds on existing evolutionary methods with a new fitness function.
The paper tackled the problem of reducing power consumption and improving accuracy in Spiking Neural Networks (SNNs) on neuromorphic hardware by optimizing for size and resilience to hardware faults, resulting in well-performing, small-sized networks with increased resilience.
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.