Groh R, Kist A (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: Institute of Electrical and Electronics Engineers Inc.
Conference Proceedings Title: 2023 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2023
Event location: Berlin, DEU
ISBN: 9798350346473
DOI: 10.1109/COINS57856.2023.10189194
Smart wearable devices require accurate, fast, and energy-efficient neural networks to allow for optimal application performance. To advance the field of neural architecture search (NAS), we introduce our end-To-end evolutionary NAS (EvoNAS) for microcontroller units that optimize both, pre-processing and neural network architectures. Each neural network architecture is assessed using the multi-objective accuracy, memory footprint, inference time, and energy consumption, to derive a common performance measure to be maximized. To ensure immediate use of all potential solutions on the microcontroller environment, we create a software-hardware chain in which each neural network is deployed to measure the inference time and power consumption directly. In a proof of concept study, we focused on the analysis of audio-based speech commands. Our experiments suggest that 2D convolutional layers with automatically set pre-processing (short-Time Fourier transforms) outperform 1D convolutional layers with raw audio signals. We show that our end-To-end EvoNAS scales with the complexity of the classification task and is still able to find constraint-preserving, and thus deployable, Pareto-optimal neural network architectures even when the classification task is more complex. Our proposed EvoNAS approach is dataset and hardware-Agnostic, allowing a universal use across a wide range of applications.
APA:
Groh, R., & Kist, A. (2023). End-To-end Evolutionary Neural Architecture Search for Microcontroller Units. In 2023 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2023. Berlin, DEU: Institute of Electrical and Electronics Engineers Inc..
MLA:
Groh, René, and Andreas Kist. "End-To-end Evolutionary Neural Architecture Search for Microcontroller Units." Proceedings of the 2023 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2023, Berlin, DEU Institute of Electrical and Electronics Engineers Inc., 2023.
BibTeX: Download