Application-oriented automatic hyperparameter optimization for spiking neural network prototyping
This work addresses the problem of efficiently optimizing SNNs for prototyping, which is crucial for researchers and developers in neuromorphic computing, though it appears incremental as it builds on existing HPO tools.
The paper tackles the challenge of hyperparameter optimization (HPO) for spiking neural networks (SNNs), which is complex due to additional neuronal parameters, by proposing an application-oriented approach using the Neural Network Intelligence (NNI) toolkit, with results demonstrated through a use case example and summarized published works.
Hyperparameter optimization (HPO) is of paramount importance in the development of high-performance, specialized artificial intelligence (AI) models, ranging from well-established machine learning (ML) solutions to the deep learning (DL) domain and the field of spiking neural networks (SNNs). The latter introduce further complexity due to the neuronal computational units and their additional hyperparameters, whose inadequate setting can dramatically impact the final model performance. At the cost of possible reduced generalization capabilities, the most suitable strategy to fully disclose the power of SNNs is to adopt an application-oriented approach and perform extensive HPO experiments. To facilitate these operations, automatic pipelines are fundamental, and their configuration is crucial. In this document, the Neural Network Intelligence (NNI) toolkit is used as reference framework to present one such solution, with a use case example providing evidence of the corresponding results. In addition, a summary of published works employing the presented pipeline is reported as a potential source of insights into application-oriented HPO experiments for SNN prototyping.