Evolution of spiking neural networks  

脉冲神经网络的发展

作　　者：TALANOV Max FEDOROVA Alina KIPELKIN Ivan VALLVERDU Jordi EROKHIN Victor TALANOV Max;FEDOROVA Alina;KIPELKIN Ivan;VALLVERDU Jordi;EROKHIN Victor(梅西纳大学工程系,意大利梅西纳;塞尔维亚人工智能研发研究所,塞尔维亚贝尔格莱德;喀山联邦大学信息技术与智能系统学院,俄罗斯喀山420008;罗巴切夫斯基大学,StoLab,俄罗斯下诺夫哥罗德603022;加泰罗尼亚高等研究院哲学系,西班牙加泰罗尼亚;意大利国家研究委员会(IMEM-CNR)电子与磁性材料研究所,意大利帕尔马43124)

机构地区：[1]Engineering Department,University of Messina,Messina,Italy [2]Institute for Artificial Intelligence R&D of Serbia,Belgrade,Serbia [3]Kazan Federal University,ITIS,Kazan 420008,Russia [4]Lobachevsky State University,StoLab,Nizhny Novgorod 603022,Russia [5]ICREA,Philosophy Department,UAB,Catalonia,Spain [6]Institute of Materials for Electronics and Magnetism,Italian National Research Council(IMEM-CNR),Parma 43124,Italy

出　　处：《宁波大学学报(理工版)》2025年第2期59-70,共12页Journal of Ningbo University:Natural Science and Engineering Edition

基　　金：Supported by CUP(J53C22003010006,J43C24000230007);ICREA2019.

摘　　要：Spiking neural networks(SNNs)represent a biologically-inspired computational framework that bridges neuroscience and artificial intelligence,offering unique advantages in temporal data processing,energy efficiency,and real-time decision-making.This paper explores the evolution of SNN technologies,emphasizing their integration with advanced learning mechanisms such as spike-timing-dependent plasticity(STDP)and hybridization with deep learning architectures.Leveraging memristors as nanoscale synaptic devices,we demonstrate significant enhancements in energy efficiency,adaptability,and scalability,addressing key challenges in neuromorphic computing.Through phase portraits and nonlinear dynamics analysis,we validate the system’s stability and robustness under diverse workloads.These advancements position SNNs as a transformative technology for applications in robotics,IoT,and adaptive low-power AI systems,paving the way for future innovations in neuromorphic hardware and hybrid learning paradigms.脉冲神经网络(SNNs)代表了一种生物启发计算框架,它将神经科学和人工智能联系在一起,在时序数据处理、能效和实时决策方面具有独特优势.探讨了SNN技术的演化过程,强调了其与高级学习机制的集成,如尖峰时间依赖可塑性(STDP)和与深度学习架构的融合.利用忆阻器作为纳米级突触设备,显著提高了能效、适应性和可扩展性,解决了神经形态计算中的关键问题.通过相图和非线性动力学分析,验证了系统在不同工作负载下的稳定性和鲁棒性.这些进步使SNNs成为机器人、物联网和自适应低功耗人工智能系统等应用领域的一项变革性技术,为神经形态硬件和混合学习范式的未来创新铺平了道路.

关 键 词：spiking neural networks MEMRISTOR phase portraits energy-efficient AI neuromorphic computing 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]