@inproceedings{3fab18eeb3904af8b7a1a9a600258a18,
title = "Machine learning on FPGAs to face the IoT revolution",
abstract = "FPGAs have been rapidly adopted for acceleration of Deep Neural Networks (DNNs) with improved latency and energy efficiency compared to CPU and GPU-based implementations. High-level synthesis (HLS) is an effective design flow for DNNs due to improved productivity, debugging, and design space exploration ability. However, optimizing large neural networks under resource constraints for FPGAs is still a key challenge. In this paper, we present a series of effective design techniques for implementing DNNs on FPGAs with high performance and energy efficiency. These include the use of configurable DNN IPs, performance and resource modeling, resource allocation across DNN layers, and DNN reduction and re-training. We showcase several design solutions including Long-term Recurrent Convolution Network (LRCN) for video captioning, Inception module for FaceNet face recognition, as well as Long Short-Term Memory (LSTM) for sound recognition. These and other similar DNN solutions are ideal implementations to be deployed in vision or sound based IoT applications.",
keywords = "FPGAs, Internet of Things, Machine Learning",
author = "Xiaofan Zhang and Anand Ramachandran and Chuanhao Zhuge and Di He and Wei Zuo and Zuofu Cheng and Kyle Rupnow and Deming Chen",
year = "2017",
month = dec,
day = "13",
doi = "10.1109/ICCAD.2017.8203875",
language = "English (US)",
series = "IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "894--901",
booktitle = "2017 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2017",
address = "United States",
note = "36th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2017 ; Conference date: 13-11-2017 Through 16-11-2017",
}