【极致中配】4K画质 Steve Brunton 基于物理约束的机器学习
Steve Brunton讲授物理约束机器学习,系统覆盖建模五步法及SINDy、PINN、神经算子等前沿方法。
- 难度
- 难度 4/5 — 融合动力系统、深度学习与物理建模,需要较强数理与ML基础
- 适合人群
- 有理工背景、想把机器学习用于科学建模的研究生与工程师
- 前置要求
- 微积分与微分方程(理解常微分/偏微分方程)、线性代数(矩阵运算与特征分析)、机器学习基础(神经网络与优化)、Python编程(科学计算与建模实践)
- 课程规模
- 24 讲 · 2049播放
主题覆盖
物理约束机器学习建模流程五步法SINDy稀疏辨识自编码器与坐标发现哈密顿神经网络拉格朗日神经网络神经常微分方程符号回归PySR傅里叶神经算子DeepONet算子网络物理信息神经网络PINN残差网络
课程大纲(24 讲)
- P1 · Physics Informed Machine Learning: High Level Overview of AI and ML in Science a32 分钟
- P2 · AI/ML+Physics Part 1: Choosing what to model [Physics Informed Machine Learning]29 分钟
- P3 · AI/ML+Physics Part 2: Curating Training Data [Physics Informed Machine Learning]25 分钟
- P4 · AI/ML+Physics Part 3: Designing an Architecture [Physics Informed Machine Learni26 分钟
- P5 · AI/ML+Physics Part 4: Crafting a Loss Function [Physics Informed Machine Learnin16 分钟
- P6 · AI/ML+Physics Part 5: Employing an Optimization Algorithm [Physics Informed Mach23 分钟
- P7 · AI/ML+Physics: Recap and Summary [Physics Informed Machine Learning]16 分钟
- P8 · AI/ML+Physics: Preview of Upcoming Modules and Bootcamps [Physics Informed Machi13 分钟
- P9 · Deep Learning to Discover Coordinates for Dynamics: Autoencoders & Physics Infor18 分钟
- P10 · Sparse Identification of Nonlinear Dynamics (SINDy): Sparse Machine Learning Mod17 分钟
- P11 · Sparse Nonlinear Dynamics Models with SINDy, Part 2: Training Data & Disambiguat12 分钟
- P12 · Sparse Nonlinear Dynamics Models with SINDy, Part 3: Effective Coordinates for P14 分钟
- P13 · Sparse Nonlinear Dynamics Models with SINDy, Part 4: The Library of Candidate No19 分钟
- P14 · Sparse Nonlinear Dynamics Models with SINDy, Part 5: The Optimization Algorithms13 分钟
- P15 · Discrepancy Modeling with Physics Informed Machine Learning13 分钟
- P16 · Hamiltonian Neural Networks (HNN) [Physics Informed Machine Learning]13 分钟
- P17 · Lagrangian Neural Network (LNN) [Physics Informed Machine Learning]13 分钟
- P18 · Neural Implicit Flow (NIF) [Physics Informed Machine Learning]9 分钟
- P19 · Neural ODEs (NODEs) [Physics Informed Machine Learning]17 分钟
- P20 · Python Symbolic Regression (PySR) [Physics Informed Machine Learning]10 分钟
- P21 · Residual Networks (ResNet) [Physics Informed Machine Learning]12 分钟
- P22 · Fourier Neural Operator (FNO) [Physics Informed Machine Learning]12 分钟
- P23 · Deep Operator Networks (DeepONet) [Physics Informed Machine Learning]12 分钟
- P24 · Physics Informed Neural Networks (PINNs) [Physics Informed Machine Learning]24 分钟
本课程卡由 AI 生成,可能存在误差,欢迎反馈。