Performance-Oriented Neural Architecture Search
This work addresses the need for performance-efficient deep learning models on edge computing devices, representing an incremental improvement by integrating hardware co-design into existing neural architecture search methods.
The paper tackled the problem of designing efficient neural architectures for deep learning by extending neural architecture search to incorporate hardware information, resulting in a 0.88% increase in TOP-1 accuracy with 1.85x latency reduction on an embedded SoC and 1.59x on a high-end GPU for keyword spotting in audio.
Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural architecture search with information about the hardware to ensure that the model designs produced are highly efficient in addition to the typical criteria around accuracy. Using the task of keyword spotting in audio on edge computing devices, we demonstrate that our approach results in neural architecture that is not only highly accurate, but also efficiently mapped to the computing platform which will perform the inference. Using our modified neural architecture search, we demonstrate $0.88\%$ increase in TOP-1 accuracy with $1.85\times$ reduction in latency for keyword spotting in audio on an embedded SoC, and $1.59\times$ on a high-end GPU.