Deep Neural Networks (DNNs) have achieved great success in a variety of machine learning (ML) applications, delivering high-quality inferencing solutions in computer vision, natural language processing, and virtual reality, etc. However, DNN-based ML applications also bring much increased computational and storage requirements, which are particularly challenging for embedded systems with limited compute/storage resources, tight power budgets, and small form factors. Challenges also come from the diverse application-specific requirements, including real-time responses, high-throughput performance, and reliable inference accuracy. To address these challenges, we introduce a series of effective design methodologies, including efficient ML model designs, customized hardware accelerator designs, and hardware/software co-design strategies to enable efficient ML applications on embedded systems.
@article{arxiv.2206.03326,
title = {Compilation and Optimizations for Efficient Machine Learning on Embedded Systems},
author = {Xiaofan Zhang and Yao Chen and Cong Hao and Sitao Huang and Yuhong Li and Deming Chen},
journal= {arXiv preprint arXiv:2206.03326},
year = {2022}
}
Comments
This article will appear as a book chapter in a new book: Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing, Springer Nature