文献阅读笔记：脉冲神经网络最新文献整理-II
研究前沿：2025年脉冲神经网络（SNN）应用进展 本文汇总了2025年SNN领域7项最新研究：1）韩国团队开发基于伯努利分布的SNN模型用于植物叶片病害检测；2）首尔大学提出节能型首次脉冲时间编码方法；3）清华大学开发多室时空反向传播的高效学习算法；4）加拿大研究显示FORCE训练下SNN学习速度受噪声影响；5）中国团队研发抗随机攻击的fMRI-SNN语音识别系统；6）印度学者将优化SNN应用于
·
| 序号 | 英文标题 | 作者及机构 | 中文翻译 | 出处 | 链接 |
|---|---|---|---|---|---|
| 1 | Behavior of Spikes in Spiking Neural Network(SNN)Model with Bernoulli for Plant Disease on Leaves | Urfa Gul，M.Junaid Gul，Gyu Sang Choi，Chang-Hyeon Park（Department of Information and Communication, Yeungnam University, Gyeongsan） | 基于伯努利的脉冲神经网络（SNN）模型在植物叶片病害中的脉冲行为 | Computers Materials&Continua 2025 第8期 | 链接 |
| 2 | Time-to-First-Spike Coding in Sensory Neuron for Energy-Efficient Spiking Neural Networks | Jae-Hyun Lee1;Se-Hyun Hwang2;Wonbin Jo2;Kang-Uk Byeon2;Joon-Kyu Han1（1Department of Materials Science and Engineering and Inter-University Semiconductor Research Center, Seoul National University, Seoul, Republic of Korea; 2Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea） | 用于节能脉冲神经网络的感觉神经元首次脉冲时间编码 | IEEE Electron Device Letters 2025 Vol.46 No.8 P1421-1424 | 链接 |
| 3 | Learning-efficient spiking neural networks with multi-compartment spatio-temporal backpropagation | Yuqian Liu1;Yuechao Wang1;Chi Zhang1;Liao Yu1;Ying Fang2,3;Feng Chen1,4（1Department of Automation, Tsinghua University, Beijing 100084, China; 2The College of Computer and Cyber Security, Fujian Normal University, Fuzhou 350117, China; 3The Digital Fujian Internet-of-thing Laboratory of Environmental Monitoring, Fujian Normal University, Fuzhou 350117, China; 4Lead contact） | 基于多室时空反向传播的高效学习脉冲神经网络 | iScience 2025 Vol.28 No.7 P112491 | 链接 |
| 4 | Comparison of FORCE trained spiking and rate neural networks shows spiking networks learn slowly with noisy, cross-trial firing rates | Thomas Robert Newton?0?2 1 ?0?2 2,?0?2Wilten Nicola?0?2 1 ?0?2 2 ?0?2 3（Affiliations 1 Department of Mathematics and Statistics, University of Calgary, Calgary, Canada; 2 Hotchkiss Brain Institute, University of Calgary, Calgary, Canada; 3 Department of Cell Biology and Anatomy, University of Calgary, Calgary, Canada） | FORCE训练的脉冲与速率神经网络比较表明脉冲网络在噪声交叉试验放电率下学习缓慢 | PLoS computational biology 2025 Vol.21 No.7 e1013224 | 链接 |
| 5 | Damage Resistance of an fMRI-Spiking Neural Network Based on Speech Recognition Against Stochastic Attack | Lei Guo?0?2 1 ?0?2 2,?0?2Huan Liu?0?2 1 ?0?2 2,?0?2Yihua Song?0?2 1 ?0?2 2,?0?2Nancheng Ma?0?2 1 ?0?2 2（Affiliations 1 Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health, School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin 300131, China; 2 State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300131, China） | 基于语音识别的fMRI-脉冲神经网络对随机攻击的抗损伤性 | Biomimetics (Basel, Switzerland) 2025 Vol.10 No.7 P415 | 链接 |
| 6 | Automated cervical cancer classification using stacked BI-LSTM and optimized spiking neural network with deer hunting optimization algorithm | Harika Vanam1;G. Vijaylaxmi2 & Vanam Sravan Kumar3（1Computer Science and Engineering, Gokaraju Lailavathi Women’s Engineering College (GLWEC), Hyderabad, India; 2Vaagdevi College of Engineering, Bollikunta, Warangal, India; 3Department of Computer Science & Engineering, Balaji Institute of Technology &Sciences, Narsampet, Warangal, India） | 基于堆叠BI-LSTM和鹿群优化算法优化脉冲神经网络的宫颈癌自动分类 | International Journal of Information Technology 2025 Vol.17 No.6 P3759-3768 | 链接 |
| 7 | 3D NoC-enabled spiking neural networks: a high-performance computing paradigm | V. Karthikeyan1 & K. Subbulakshmi2（1Department of ECE, Mepco Schlenk Engineering College, Sivakasi, Tamilnadu, India; 2Department of ECE, Sethu Institute of Technology, Pulloor, Kariapatti, Virudhunagar, Tamilnadu, India） | 基于3D NoC的脉冲神经网络：一种高性能计算范式 | Evolving Systems 2025 Vol.16 No.3 | 链接 |
| 8 | Phasic attractors for flexible and adaptive working memory in spiking recurrent neural networks | Willian S Gir?0?0o*;Thomas F Tiotto*;Jelmer P Borst;Niels A Taatgen;Elisabetta Chicca | 脉冲递归神经网络中用于灵活自适应工作记忆的相位吸引子 | Neuromorphic Computing and Engineering 2025 Vol.5 No.3 P034004 | 链接 |
| 9 | A spiking photonic neural network of 40 000 neurons, trained with latency and rank-order coding for leveraging sparsity | Ria Talukder;Anas Skalli;Xavier Porte;Simon Thorpe;Daniel Brunner*（1FEMTO-ST Institute/Optics Department, Université Marie et Louis Pasteur , CNRS UMR, 6174 Besan?0?4on, France; 2Institute of Photonics, Department of Physics, University of Strathclyde , 99 George str., Glasgow G1 1RD, United Kingdom; 3Centre de Recherche Cerveau et Cognition CERCO UMR5549, CNRS—Université Toulouse III , Toulouse, France） | 基于延迟和秩次编码训练的40,000神经元脉冲光子神经网络以利用稀疏性 | Neuromorphic Computing and Engineering 2025 Vol.5 No.3 P034003 | 链接 |
| 10 | Integrated dynamic spiking neural P systems for fault line selection in distribution network | Song Ma1,2;Qiang Yang2,3;Gexiang Zhang2;Fei Li1;Fan Yu4 & …Xiu Yin5（1National and Local Joint Engineering Laboratory for Renewable Energy Access to Grid Technology, Hefei University of Technology, No. 193 Tunxi Road, Hefei, 230009, Anhui, China; 2School of Automation, Chengdu University of Information Technology, No. 24 Block 1, Xuefu Road, Chengdu, 610225, Anhui, China; 3Key Laboratory of Natural Disaster Monitoring & Early Warning and Assessment of Jiangxi Province, Jiangxi Normal University, No. 99 Ziyang Avenue, Nanchang, 330022, Jiangxi, China; 4School of Computer Science and Cyber Security, Chengdu University of Technology, No. 1, East Third Road, Erxianqiao, Chenghua District, Chengdu, 610059, Sichuan, China; 5Business School, Shandong Normal University, No. 88 East Wenhua Road, Lixia District, Shandong, Jinan, China, 250014） | 用于配电网故障选线的集成动态脉冲神经P系统 | Natural Computing 2025 Vol.24 No.2 P337-348 | 链接 |
| 11 | Correction: Integrated dynamic spiking neural P systems for fault line selection in distribution network | Song Ma1,2;Qiang Yang2,3;Gexiang Zhang2;Fei Li1;Fan Yu4 & …Xiu Yin5（1National and Local Joint Engineering Laboratory for Renewable Energy Access to Grid Technology, Hefei University of Technology, No. 193 Tunxi Road, Hefei, 230009, Anhui, China; 2School of Automation, Chengdu University of Information Technology, No. 24 Block 1, Xuefu Road, Chengdu, 610225, Anhui, China; 3Key Laboratory of Natural Disaster Monitoring & Early Warning and Assessment of Jiangxi Province, Jiangxi Normal University, No. 99 Ziyang Avenue, Nanchang, 330022, Jiangxi, China; 4School of Computer Science and Cyber Security, Chengdu University of Technology, No. 1, East Third Road, Erxianqiao, Chenghua District, Chengdu, 610059, Sichuan, China; 5Business School, Shandong Normal University, No. 88 East Wenhua Road, Lixia District, Shandong, 250014, Jinan, China） | 更正：用于配电网故障选线的集成动态脉冲神经P系统 | Natural Computing 2025 Vol.24 No.2 P349 | 链接 |
| 12 | Toward High-Accuracy and Low-Latency Spiking Neural Networks With Two-Stage Optimization | Ziming Wang,?0?2Yuhao Zhang,?0?2Shuang Lian,?0?2Xiaoxin Cui,?0?2Rui Yan,?0?2Huajin Tang | 基于两阶段优化的高精度低延迟脉冲神经网络 | IEEE transactions on neural networks and learning systems 2025 Vol.36 No.2 P3189-3203 | 链接 |
| 13 | Advancing EEG based stress detection using spiking neural networks and convolutional spiking neural networks | Aaditya Joshi1;Paramveer Singh Matharu1;Lokesh Malviya1;Manoj Kumar1;null;Akshay Jadhav2（1VIT Bhopal University, Sehore, Madhya Pradesh, India; 2Manipal University Jaipur, Jaipur, Rajasthan, India） | 利用脉冲神经网络和卷积脉冲神经网络推进基于EEG的压力检测 | Scientific Reports 2025 Vol.15 No.1 P26267 | 链接 |
| 14 | A Precise and Low Power Analog Spiking Neural Network Exploiting Pre-Charged Current Mode Synapses and Coarse-Fine Neuron Comparators | Kyu-Dong Hwang;Kwang-Il Oh;Jae-Jin Lee;Min-Woo Kim;Byung-Do Yang（AI SoC Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea Contribution: Conceptualization, Data curation, Formal analysis, Funding acquisition, ?6?7Investigation, Methodology, Project administration, Resources, Software, Supervision, Validation, Visualization, Writing - original draft, Writing - review & editing; AI SoC Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea Contribution: Conceptualization, Methodology, Visualization, Writing - original draft; AI SoC Research Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea Contribution: ?6?7Investigation, Project administration, Supervision; Electronics Engineering, Chungbuk National University, Cheongju, South Korea Contribution: Data curation, Visualization; Electronics Engineering, Chungbuk National University, Cheongju, South Korea Contribution: Conceptualization, Data curation, Formal analysis, Methodology, Resources, Software, Supervision） | 利用预充电电流模式突触和粗精神经元比较器的高精度低功耗模拟脉冲神经网络 | Electronics Letters 2025 Vol.61 No.1 e70318 | 链接 |
| 15 | BAL-SNN: Balanced Active Learning for Spiking Neural Networks | Meiling Zhong1,2;Chunyan She1,2;bingrui Xu1;qing Yang1,2;shukai Duan1,3;lidan Wang1,2,4（1College of Artificial Intelligence, Southwest University, Chongqing, 400715, China; 2Chongqing Key Laboratory of Brain-inspired Computing and Intelligent chips, Chongqing, 400715, China; 3Joint Engineering Research Center of Intelligent Transmission & Control Technology, National & Local, Chongqing, 400715, China; 4Ministry of Education, Key Laboratory of Luminescence Analysis and Molecular Sensing (Southwest University), Southwest University, Chongqing, 400715, China） | BAL-SNN：脉冲神经网络的平衡主动学习 | Knowledge-Based Systems 2025 P114097 | 链接 |
| 16 | Hyper Lightweight Neural Networks towards Spike-Driven Deep Residual Learning | Shilong Jing1,2;Hengyi Lv1;Yuchen Zhao1;Hechong Wang1,2;Guo Guangsha1,2;Xianda Xu1,2;Yisa Zhang1;Yang Feng1（1Fine Mechanics and Physics, Changchun Institute of Optics, Chinese Academy of Sciences, China; 2University of Chinese Academy of Sciences, China） | 面向脉冲驱动深度残差学习的超轻量级神经网络 | Knowledge-Based Systems 2025 P114099 | 链接 |
| 17 | Advances in Large-Scale Spiking Neural Networks: Learning, Simulation, and Deployment | Rui Wang;Yifan Liu;Heng Xue | 大规模脉冲神经网络的进展：学习、仿真与部署 | 2025 | 链接 |
| 18 | Synergies and Divergences Between Spiking Neural Networks and Large Language Models | Zhen Huan;Heng Xue;Zhen Li | 脉冲神经网络与大型语言模型的协同与分歧 | 2025 | 链接 |
| 19 | Energy-Efficient and Intelligent ISAC in V2X Networks with Spiking Neural Networks-Driven DRL | Chen Shang1;Jiadong Yu1;Dinh Thai Hoang2（1Internet of Things Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China; 2School of Electrical and Data Engineering, University of Technology Sydney, Australia） | 基于脉冲神经网络驱动DRL的V2X网络中节能智能ISAC | IEEE Transactions on Wireless Communications 2025 P1 | 链接 |
| 20 | Combining aggregated attention and transformer architecture for accurate and efficient performance of Spiking Neural Networks | Hangming Zhang1;Alexander Sboev2,3;Roman Rybka2,3;Qiang Yu1,4（1College of Intelligence and Computing, Tianjin University, Tianjin, 300354, China; 2National Research Center Kurchatov Institute, Moscow, 123182, Russia; 3National Research Nuclear University MEPhI, Moscow, 115409, Russia; 4College of Computer and Information Engineering, Tianjin Normal University, Tianjin, 300387, China） | 结合聚合注意力和Transformer架构实现脉冲神经网络的精准高效性能 | Neural Networks 2025 Vol.191 P107789 | 链接 |
| 21 | A Brain-Inspired Hybrid Plasticity Feedforward-Inhibitory Spike Neural Network for Olfactory Perception | Hongshuo Fu1;Ping Fu1;Xiaoyang Lu1;Bingjie Sun1;Bing Liu1（1School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China） | 用于嗅觉感知的脑启发混合可塑性前馈-抑制脉冲神经网络 | IEEE Sensors Journal 2025 P1 | 链接 |
| 22 | Recurrent spiking neural networks as models of the entorhinal–hippocampal system for path integration: Grid cells and beyond | Ruilan Gao1;Changjian Jiang1;Yu Zhang1,2（1State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, 310027, China; 2Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province, Hangzhou, 310027, China） | 作为路径整合内嗅-海马系统模型的递归脉冲神经网络：网格细胞及其他 | Neurocomputing 2025 Vol.651 P130814 | 链接 |
| 23 | Dual-model spiking neural network for remote sensing image classification using mutual knowledge distillation | Zhen Cao1;Ju Liu1;Qi Sun1;Biao Hou1;Hao Zhu1;Lei Guo1;Yifan Ge2;Yulong Wang2;Licheng Jiao1（1School of Artificial Intelligence, Xidian University, Xi’an, 710126, Shaanxi, China; 2Beijing Aerospace Automatic Control Institute, Beijing, 100854, China） | 基于互知识蒸馏的双模型脉冲神经网络用于遥感图像分类 | Neurocomputing 2025 P130721 | 链接 |
| 24 | DAFF-SNN: Dual Attention-driven and Feature Fusion-based Spiking Neural Network for Epilepsy Detection based on Electroencephalogram | Tao Zhang,?0?2Lanqi He,?0?2Dingguo Zhang,?0?2Mingyang Li,?0?2Zhiyong Chang | DAFF-SNN：基于双注意力驱动和特征融合的脉冲神经网络用于基于脑电图的癫痫检测 | IEEE journal of biomedical and health informatics 2025 | 链接 |
| 25 | A Spiking Neural Network for Hyperspectral Image Classification | Zhengda Han;Yu Li（School of Geomatics, Liaoning Technical University, Fuxin, China） | 用于高光谱图像分类的脉冲神经网络 | 2025 6th International Conference on Geology, Mapping and Remote Sensing (ICGMRS) Wuhan, China 2025 | 链接 |
| 26 | On the Trustworthiness of Spiking Neural Networks and Neuromorphic Systems | Theofilos Spyrou;Haralampos-G. Stratigopoulos;Ihsen Alouani;Said Hamdioui;Anteneh Gebregiorgis（Computer Engineering Lab, Delft University of Technology, Delft, The Netherlands; CNRS, LIP6, Sorbonne Université, Paris, France; UPHF, INSA Hauts-De-France, CNRS-IEMN, France","Queen’s University, Belfast, United Kingdom） | 脉冲神经网络和神经形态系统的可信度研究 | 2025 IEEE European Test Symposium (ETS) Tallinn, Estonia 2025 | 链接 |
| 27 | Realtime-Capable Hybrid Spiking Neural Networks for Neural Decoding of Cortical Activity | Jann Krausse;Alexandru Vasilache;Klaus Knobloch;Juergen Becker（Karlsruhe Institute of Technology, Karlsruhe, Germany",“Infineon Technologies, Dresden, Germany; Karlsruhe Institute of Technology, Karlsruhe, Germany”,"FZI Research Center for Information Technology, Karlsruhe, Germany; Infineon Technologies, Dresden, Germany; Karlsruhe Institute of Technology, Karlsruhe, Germany） | 用于皮层活动神经解码的实时混合脉冲神经网络 | 2025 Neuro Inspired Computational Elements (NICE) Heidelberg, Germany 2025 | 链接 |
| 28 | Input-Triggered Hardware Trojan Attack on Spiking Neural Networks | Spyridon Raptis;Paul Kling;Ioannis Kaskampas;Ihsen Alouani;Haralampos-G. Stratigopoulos（1 CIAN - Circuits Intégrés Numériques et Analogiques; 2 QUB - Queen’s University [Belfast]） | 脉冲神经网络的输入触发硬件木马攻击 | IEEE International Symposium on Hardware Oriented Security and Trust (HOST) San Jose, CA, USA 2025 | 链接 |
| 29 | MMT-SNN: Markovian decision and multi-threshold spike delivery integrated adaptive spiking neural network for tactile object recognition | Jing Yang1,2,3;Zukun Yu2;Changfu Zhang4;Shaobo Li2,3;Lin Li4;Zhidong Su5;Yixiong Feng3（1Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 201100, China; 2Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education, Guizhou University, Guiyang 550025, China; 3State Key Laboratory of Public Big Data Ministry of Education, Guizhou University, Guiyang 550025, China; 4Guizhou CASI Cloud Technology Co., Ltd., Guiyang 550014, China; 5School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK 74078, USA） | MMT-SNN：用于触觉物体识别的马尔可夫决策和多阈值脉冲传递集成自适应脉冲神经网络 | Expert Systems with Applications 2026 Vol.295 P128850 | 链接 |
| 30 | SPSNet: A spiking neural network with relation graphs for sleep stage classification based on polysomnography | Yuchen Pan1;Kebin Jia1;Zheng Jin1;Zhe Li1（1School of Information Science and Technology, Beijing University of Technology, Beijing, 100124, China） | SPSNet：基于多导睡眠图的关系图脉冲神经网络用于睡眠阶段分类 | Biomedical Signal Processing and Control 2026 Vol.111 P108227 | 链接 |
魔乐社区（Modelers.cn) 是一个中立、公益的人工智能社区，提供人工智能工具、模型、数据的托管、展示与应用协同服务，为人工智能开发及爱好者搭建开放的学习交流平台。社区通过理事会方式运作，由全产业链共同建设、共同运营、共同享有，推动国产AI生态繁荣发展。
更多推荐
29
0- 0
已为社区贡献2条内容
所有评论(0)