Training and Deploying Spiking NN Applications to the Mixed-Signal Neuromorphic Chip Dynap-SE2 with Rockpool

Mixed-signal neuromorphic processors provide extremely low-power operation for edge inference workloads, taking advantage of sparse asynchronous computation within Spiking Neural Networks (SNNs). However, deploying robust applications to these devices is complicated by limited controllability over analog hardware parameters, unintended parameter and dynamics variations of analog circuits due to fabrication non-idealities. Here we demonstrate a novel methodology for offline training and deployment of spiking neural networks (SNNs) to the mixed-signal neuromorphic processor Dynap-SE2. The methodology utilizes an unsupervised weight quantization method to optimize the network's parameters, coupled with adversarial parameter noise injection during training. The optimized network is shown to be robust to the effects of quantization and device mismatch, making the method a promising candidate for real-world applications with hardware constraints. This work extends Rockpool, an open-source deep-learning library for SNNs, with support accurate simulation of mixed-signal SNN dynamics. Our approach simplifies the development and deployment process for the neuromorphic community, making mixed-signal neuromorphic processors more accessible to researchers and developers.