Data Aware Differentiable Neural Architecture Search for Tiny Keyword Spotting Applications
This addresses the resource footprint problem for TinyML applications, offering a novel approach to system design.
The paper tackled the complexity of designing TinyML systems by introducing Data Aware Differentiable Neural Architecture Search, which co-optimizes model architecture and input data parameters, resulting in lean and highly accurate keyword spotting systems.
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 co-optimize 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.