@inproceedings{24fd2214ab394da08d1d58f7553d25bf,
title = "A 47.4µJ/epoch trainable deep convolutional neural network accelerator for in-situ personalization on smart devices",
abstract = "A scalable deep learning accelerator supporting both inference and training is implemented for device personalization of deep convolutional neural networks. It consists of three processor cores operating with distinct energy-efficient dataflow for different types of computation in CNN training. Two cores conduct forward and backward propagation in convolutional layers and utilize a masking scheme to reduce 88.3% of intermediate data to store for training. The third core executes weight update process in convolutional layers and inner product computation in fully connected layers with a novel large window dataflow. The system enables 8-bit fixed point datapath with lossless training and consumes 47.4µJ/epoch for a customized deep CNN model.",
author = "Seungkyu Choi and Jaehyeong Sim and Myeonggu Kang and Yeongjae Choi and Hyeonuk Kim and Kim, {Lee Sup}",
note = "Publisher Copyright: {\textcopyright} 2019 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.; null ; Conference date: 04-11-2019 Through 06-11-2019",
year = "2019",
month = nov,
doi = "10.1109/A-SSCC47793.2019.9056972",
language = "English",
series = "Proceedings - 2019 IEEE Asian Solid-State Circuits Conference, A-SSCC 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "57--60",
booktitle = "Proceedings - 2019 IEEE Asian Solid-State Circuits Conference, A-SSCC 2019",
}