Application-oriented automatic hyperparameter optimization for spiking neural network prototyping
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908600975228928 |
|---|---|
| author | Fra, Vittorio |
| author_facet | Fra, Vittorio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12172 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Application-oriented automatic hyperparameter optimization for spiking neural network prototyping Fra, Vittorio Neural and Evolutionary Computing Machine Learning 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. |
| title | Application-oriented automatic hyperparameter optimization for spiking neural network prototyping |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2502.12172 |