Data Aware Differentiable Neural Architecture Search for Tiny Keyword Spotting Applications
Yujia Shi, Emil Njor, Pablo Martínez-Nuevo, Sven Ewan Shepstone, Xenofon Fafoutis · 2025
The success of Machine Learning is increasingly tempered by its significant resource footprint, driving interest in efficient paradigms like TinyML. However, the inherent complexity of designing TinyML systems hampers their broad adoption. To reduce this complexity, we introduce “Data Aware Differentiable Neural Architecture Search”. Unlike conventional Differentiable Neural Architecture Search, our approach expands the search space to include data configuration parameters alongside architectural choices. This enables Data Aware Differentiable Neural Architecture Search to cooptimize model architecture and input data characteristics, effectively balancing resource usage and system performance for TinyML applications. Initial results on keyword spotting demonstrate that this novel approach to TinyML system design can generate lean but highly accurate systems.