Deploying Deep Neural Networks in the Embedded Space
This addresses the challenge for IoT and mobile developers needing to run AI applications on resource-constrained devices, but it appears incremental as it summarizes existing work without presenting new results.
The paper tackles the problem of efficiently deploying deep neural networks on embedded platforms, summarizing recent work on optimized mapping techniques including toolflows, classifiers, and model design to enable sophisticated deep learning on mobile and embedded systems.
Recently, Deep Neural Networks (DNNs) have emerged as the dominant model across various AI applications. In the era of IoT and mobile systems, the efficient deployment of DNNs on embedded platforms is vital to enable the development of intelligent applications. This paper summarises our recent work on the optimised mapping of DNNs on embedded settings. By covering such diverse topics as DNN-to-accelerator toolflows, high-throughput cascaded classifiers and domain-specific model design, the presented set of works aim to enable the deployment of sophisticated deep learning models on cutting-edge mobile and embedded systems.