计算机工程与应用2025，Vol.61Issue(14)：20-36,17.DOI:10.3778/j.issn.1002-8331.2409-0436
深度学习中结合哈密顿力学的神经网络研究进展
Advances in Neural Networks Combined with Hamiltonian Mechanics in Deep Learning
摘要
Abstract
Neural networks based on Hamiltonian mechanics have become an important research direction in the field of natural language processing,which can not only solve the problem of gradient disappearance in deep learning,but also provide a new way for researchers to explore the interpretibility of neural networks and solve the current difficult prob-lems in deep learning.It utilizes the principles of classical mechanics,updates the network state through the Hamiltonian function,and uses the energy conservation property to effectively improve the accuracy of the model,and also makes an important contribution to solving the gradient problem in deep learning.Firstly,the main motivation and theoretical basis of deep learning guided by Hamiltonian mechanics are briefly introduced.Secondly,the neural network based on Hamilto-nian mechanics is discussed in detail,and its characteristics,application scenarios and limitations are summarized.Finally,the problems and challenges of the combination of Hamiltonian mechanics and neural networks in the field of natural language processing are discussed,and the future development is prospected to provide a reference for further research.关键词
哈密顿力学/梯度消失/神经网络/自然语言处理Key words
Hamiltonian dynamics/gradient vanishing/neural networks/natural language processing分类
信息技术与安全科学引用本文复制引用
梁永琦,白双成,张志一..深度学习中结合哈密顿力学的神经网络研究进展[J].计算机工程与应用,2025,61(14):20-36,17.基金项目
国家社科基金(20XYY027) （20XYY027）
内蒙古自治区自然科学基金重点项目(2023ZD10,2022ZD05) （2023ZD10,2022ZD05）
内蒙古自治区高等学校创新团队发展计划支持项目(NMGIRT2414). （NMGIRT2414）
