Nature Communications (Jun 2022)
A framework for the general design and computation of hybrid neural networks
- Rong Zhao,
- Zheyu Yang,
- Hao Zheng,
- Yujie Wu,
- Faqiang Liu,
- Zhenzhi Wu,
- Lukai Li,
- Feng Chen,
- Seng Song,
- Jun Zhu,
- Wenli Zhang,
- Haoyu Huang,
- Mingkun Xu,
- Kaifeng Sheng,
- Qianbo Yin,
- Jing Pei,
- Guoqi Li,
- Youhui Zhang,
- Mingguo Zhao,
- Luping Shi
Affiliations
- Rong Zhao
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Zheyu Yang
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Hao Zheng
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Yujie Wu
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Faqiang Liu
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Zhenzhi Wu
- Lynxi Technologies Co., Ltd
- Lukai Li
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Feng Chen
- Department of Automation, Tsinghua University
- Seng Song
- Department of Biomedical Engineering, Tsinghua University
- Jun Zhu
- Department of Computer Science and Technology, Tsinghua University
- Wenli Zhang
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Haoyu Huang
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Mingkun Xu
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Kaifeng Sheng
- Lynxi Technologies Co., Ltd
- Qianbo Yin
- Lynxi Technologies Co., Ltd
- Jing Pei
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Guoqi Li
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- Youhui Zhang
- Department of Computer Science and Technology, Tsinghua University
- Mingguo Zhao
- Department of Automation, Tsinghua University
- Luping Shi
- Center for Brain-Inspired Computing Research (CBICR), Beijing Advanced Innovation Center for Integrated Circuits, Optical Memory National Engineering Research Center, & Department of Precision Instrument, Tsinghua University
- DOI
- https://doi.org/10.1038/s41467-022-30964-7
- Journal volume & issue
-
Vol. 13,
no. 1
pp. 1 – 12
Abstract
Hybrid neural networks combine advantages of spiking and artificial neural networks in the context of computing and biological motivation. The authors propose a design framework with hybrid units for improved flexibility and efficiency of hybrid neural networks, and modulation of hybrid information flows.
