个人邮箱：junxian_he@cqu.edu.cn

        何俊贤，2019年获得重庆大学电子信息工程专业学士学位，并推荐免试攻读重庆大学微电子于通信工程学院硕士研究生，2020年通过博士生入学申请考核，提前转为硕博连读。主研及参与多项国家级和省部级重点项目，曾获得2022年第八届中国国际“互联网+”大学生创新创业大赛重庆赛区金奖（团队负责人）、2019年兆易创新杯第十四届研究生电子设计竞赛全国总决赛二等奖、2018年重庆市TI杯大学生电子设计竞赛三等奖，等等。2023年9月-2024年9月于哈佛大学医学院 Schepens视觉科学研究中心交流访学，期间主要研究方向为：基于多模态人工智能大模型的视障辅助系统研究设计。共发表19篇学术论文，申请8项国家发明专利。目前研究兴趣包括类脑深度脉冲神经网络算法模型、神经形态深度处理器芯片设计。

项目经历

  1. 高精度的激光中心线提取算法. 北京犀灵视觉科技有限公司横向项目，2023-2023，1万，主持

发表论文

  1. A Visual Cortex-Inspired Edge Neuromorphic Hardware Architecture With On-Chip Multi-Layer STDP Learning
        Junxian He, Min Tian, Ying Jiang, Haibing Wang, Tengxiao Wang, Xichuan Zhou, Liyuan Liu, Nanjian Wu, Ying Wang, Cong Shi*. Computers and Electrical Engineering, 2024, 2024, 120:109806.（SCI, 1区）

  2. Can ChatGPT assist visually impaired people with micro-navigation?
        Junxian He, Shrinivas Pundlik, Gang Luo. Preprint at https://arxiv.org/abs/2106.07030 (2024)

  3. MorphBungee: A 65-nm 7.2-mm2 27-μJ/image Digital Edge Neuromorphic Chip with On-Chip 802-frame/s Multi-Layer Spiking Neural Network Learning
        Tengxiao Wang, Min Tian, Haibing Wang, Zhengqing Zhong, Junxian He, Fang Tang, Xichuan Zhou, Yingcheng Lin, Shuang-Ming Yu, Liyuan Liu, Cong Shi*. IEEE Transactions on Biomedical Circuits and Systems, 2024, doi: 10.1109/TBCAS.2024.3412908 (Early Access)（SCI，1区）

  4. An 8-T Processing-in-Memory SRAM Cell-Based Pixel-Parallel Array Processor for Vision Chips
         Leyi Chen, Cong Shi, Junxian He, Jianyi Yu, Haibing Wang, Jing Lu, Liyuan Liu, Nanjian Wu, Min Tian*. IEEE Transactions on Circuits and Systems I: Regular Papers: 2023, 70(11), 4249-4259.（SCI，1区）

  5. MorphBungee: A 65nm 7.2mm2 27μJ/image Digital Edge Neuromorphic Chip with On-Chip 802 frame/s Multi-layer Spiking Neural Network Learning
        Tengxiao Wang, Min Tian, Zhengqing Zhong, Haibing Wang, Junxian He, Fang Tang, Xichuan Zhou, Shuangming Yu, Nanjian Wu, Liyuan Liu, Cong Shi*, 2023 IEEE Asian Solid-State Circuits Conference (ASSCC), 2023, 1-3.

  6. Live Demonstration: Face Recognition at The Edge Using Fast On-Chip Deep Learning Neuromorphic Chip
        Zhengqing Zhong, Tengxiao Wang, Haibing Wang, Zhihua Zhou, Junxian He, Fang Tang, Xichuan Zhou, Shuangming Yu, Liyuan Liu, Nanjian Wu, Min Tian, Cong Shi*. 2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS), 2023, 1-2.

  7. Low-Cost Real-Time VLSI System for High-Accuracy Optical Flow Estimation Using Biological Motion Features and Random Forests
        Cong Shi, Junxian He, Shrinivas Pundlik, Xichuan Zhou*, Nanjian Wu, Gang Luo. Science China Information Sciences: 2023, 66(5), 159401.（SCI，2区）

  8. High-Accuracy Deep ANN-to-SNN Conversion Using Quantization-Aware Training Framework and Calcium-Gated Bipolar Leaky Integrate & Fire Neuron
         Haoran Gao, Junxian He, Haibing Wang, Tengxiao Wang, Zhengqing Zhong, Jianyi Yu, Ying Wang, Min Tian, Cong Shi*. Frontiers in Neuroscience: 2023, 17, 1141701.（SCI，2区）

  9. An Edge Neuromorphic Hardware with Fast On-Chip Error-Triggered Learning on Compressive Sensed Spikes
         Cong Shi, Jingya Zhang, Tengxiao Wang, Zhengqing Zhong, Junxian He, Haoran Gao, Jianyi Yu, Ping Li, Min Tian*. IEEE Transactions on Circuits and Systems II: Express Briefs: 2023, 70(7), 2665-2669.（SCI，2区）

  10. A Configurable On-Chip Spike Encoding Network Based on Dual-Mode Integrate & Fire Neurons
         Zhengqing Zhong, Yunpeng Tuo*, Haibing Wang, Tengxiao Wang, Junxian He, Min Tian, Cong Shi. IEEE 6th Information Technology, Networking, Electronic and Automation Control Conference(ITNEC): 2023, 1445-1449.

  11. An 8-T Processing-in-Memory SRAM Cell-Based Pixel-Parallel Array Processor for Vision Chips
         Leyi Chen, Junxian He, Jianyi Yu, Haibing Wang, Jing Lu, Liyuan Liu, Nanjian Wu, Cong Shi, Min Tian*. IEEE Asia Pacific Conference on Circuits and Systems (APCCAS): 2022, 1-5.(Best Paper Award)

  12. TEDOP: a Tiny Event-Driven Neural Network Hardware Core Enabling On-Chip Spike-Driven Synaptic Plasticity
         Cong Shi, Sihao Chen, Haibing Wang, Zhengqing Zhong, Ping Li, Junxian He, Tengxiao Wang, Jianyi Yu, Min Tian*. IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA): 2022, pp. 62-63.

  13. MorphBungee: An Edge Neuromorphic Chip for High-Accuracy On-Chip Learning of Multiple-Layer Spiking Neural Networks
        Tengxiao Wang, Haibing Wang, Junxian He, Zhengqing Zhong, Fang Tang, Xichuan Zhou, Shuang-Ming Yu, Liyuan Liu, Nanjian Wu, Min Tian, Cong Shi*. IEEE Biomedical Circuits and Systems Conference (BioCAS): 2022, 255-259.

  14. TripleBrain: A Compact Neuromorphic Hardware Core with Fast On-Chip Self-Organizing and Reinforcement Spike-Timing Dependent Plasticity
        Haibing Wang, Zhen He, Tengxiao Wang, Junxian He, Xichuan Zhou, Ying Wang, Liyuan Liu, Nanjian Wu, Min Tian, Cong Shi. IEEE Transactions on Biomedical Circuits and Systems. 2022, 16(4), 636-650.（SCI，2区）

  15. TripleBrain: An Edge Neuromorphic Architecture for High-accuracy Single-layer Spiking Neural Network with On-chip Self-organizing and Reinforcement Learning
         Haibing Wang, Zhen He, Jinsong Rao, Tengxiao Wang, Junxian He, Min Tian, Xichuan Zhou, Liyuan Liu, Nanjian Wu, Cong Shi*. IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA): 2021, 88-89.

  16. A Pixel-Parallel Array Processor without Computational Logic for Computational Image Sensors
        Yingcheng Lin, Rui Li, Wei He, Xichuan Zhou, Junxian He, Ping Li, Liyuan Liu, Nanjian Wu, Cong Shi*. IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA): 2021, 51-52.

  17. DeepTempo: a Hardware-Friendly Direct Feedback Alignment Multi-Layer Tempotron Learning Rule for Deep Spiking Neural Networks
         Cong Shi*, Tengxiao Wang, Junxian He, Jianghao Zhang, Liyuan Liu, Nanjian Wu. IEEE Transactions on Circuits and Systems II: Express Briefs: 2021, 68(5), 1581-1585. （SCI，2区，invited paper）

  18. CompSNN: A Lightweight Spiking Neural Network Based on Spatiotemporally Compressive Spike Features
         Tengxiao Wang, Cong Shi*, Xichuan Zhou, Yingcheng Lin, Junxian He, Ping Gan, Ping Li, Ying Wang, Liyuan Liu, Nanjian Wu, Gang Luo. Neurocomputing: 2021, 425(15), 96-106. （SCI，2区）

  19. A High-speed Low-cost CNN Inference Accelerator for Depthwise Separable Convolution
         Yingcheng Lin, Rui Li, Wei He, Xichuan Zhou, Junxian He, Ping Li, Ying Jiang, Liyuan Liu, Nanjian Wu, Cong Shi*. IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA): 2020, 63-64.

  20. A High-speed Low-cost VLSI System Capable of On-chip Online Learning for Dynamic Vision Sensor Data Classification
         Wei He, Jinguo Huang, Tengxiao Wang, Yingcheng Lin, Junxian He, Xichuan Zhou, Ping Li, Ying Wang, Nanjian Wu, Cong Shi*. Sensors: 2020, 20(17), 4715. （SCI，3区）

  21. A Hardware System for Fast AER Object Classification with On-chip Online Learning
         Jinguo Huang, Wei He, Xichuan Zhou, Junxian He, Ying Wang, Cong Shi, Yingcheng Lin*. IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA): 2019, 85-86.

  22. 20,000-fps Visual Motion Magnification on Pixel-parallel Vision Chip
         Junxian He, Xichuan Zhou, Yingcheng Lin, Chonglei Sun, Cong Shi*, Nanjian Wu, Gang Luo. IEEE International Conference on ASIC (ASICON): 2019, 1-4.

  23. 基于仿生运动能量特征的光流计算芯片设计综述
         何俊贤, 黄进国, 石匆*. 微纳电子与智能制造: 2019, 1(3), 141-150

发明专利

  1. 网络结构可配置的类脑芯片架构.
    石匆*, 王腾霄, 田敏, 王海冰, 钟正青, 何俊贤, 蒋颖. 中国，公开号：CN117273100A，2023-12-22

  2. 事件驱动类型芯片中突触权重更新方法、芯片、电子设备.
    石匆*, 王海冰, 田敏, 何俊贤, 王腾霄, 喻剑依, 高灏然, 张靖雅, 陈乐毅, 陈思豪, 庹云鹏. 中国，公开号：CN116629331A，2023-08-22

  3. 基于Ca-LIF神经元模型的Spike-BP片上学习方法、系统及处理器.
    石匆*, 高灏然, 田敏, 何俊贤, 王腾霄, 喻剑依, 王海冰, 陈思豪, 张靖雅, 庹云鹏, 陈乐毅. 中国，公开号：CN116629344A，2023-08-22

  4. 基于全脉冲HMAX模型的多层卷积类脑芯片.
    石匆*, 何俊贤, 王海冰, 王腾霄, 张靖雅, 高灏然. 中国，公开号：CN116562350A，2023-08-08

  5. 一种基于液体状态机的脉冲神经网络架构.
    石匆*, 陈乐毅, 田敏, 何俊贤, 王腾霄, 王海冰, 喻剑依, 高灏然. 中国，公开号：CN116562354A，2023-08-08

  6. 深层脉冲神经网络模型及深层SNN片上实时学习处理器.
    石匆*，张靖雅, 田敏, 王腾霄, 何俊贤, 喻剑依, 高灏然, 王海冰, 陈乐毅, 陈思豪, 庹云鹏. 中国，公开号：CN116562344A，2023-08-08

  7. 基于双模式积分点火神经元的片上脉冲编码器.
    石匆*, 庹云鹏, 钟正青, 田敏, 王海冰, 王腾霄, 何俊贤, 陈乐毅, 张靖雅, 王丽, 陈思豪, 高灏然. 中国，公开号：CN116050487A，2023-05-02

  8. 轻量级片上学习FPGA硬件架构及其设计方法.
    石匆*, 张靖雅, 田敏, 王腾霄, 王海冰, 何俊贤, 卢靖, 高灏然. 中国，公开号：CN115115039A，2022-09-27

  9. 一种低光照小像素CFA采样与边缘计算设备适用的去马赛克方法.
    石匆*, 任静, 李睿, 王海冰, 高灏然, 何俊贤, 王腾霄, 王丽. 中国，公开号：CN115082315A，2022-09-20

  10. 存内计算装置及其控制方法.
    石匆*, 陈乐毅, 田敏, 王海冰, 喻剑依, 何俊贤. 中国，公开号：CN115064197A，2022-09-16

  11. 基于简化SDSP算法的轻量级片上学习方法、系统及处理器.
    陈思豪, 石匆*, 田敏, 何俊贤, 王腾霄, 王海冰, 高灏然, 庹云鹏. 中国，公开号：CN115018058A，2022-09-06

  12. 基于忆阻器的可片上强化学习脉冲GAN模型及设计方法. 
    石匆*, 卢靖, 田敏, 王海冰, 喻剑依, 何俊贤, 王腾霄, 高灏然. 中国，公开号：CN114943329A，2022-08-25

  13. 基于脉冲神经网络的轻量级片上学习方法、系统及处理器.
    王海冰, 石匆*, 田敏, 王腾霄, 何俊贤, 何祯. 中国，公开号：CN114091663A，2022-2-25

  14. 基于脉冲神经网络的实时深度学习方法、系统及处理器.
    王腾霄, 石匆*, 田敏, 何俊贤, 王海冰, 喻剑依. 中国，公开号：CN114065922A，2022-2-18
By