Tutorial Materials

1. Python & ML Tutorial

• Machine Learning from Scratch Derivations in Concept and Code. 从零开始推导机器学习的概念与代码实现。
• Dive into Deep Learning (动手学深度学习) Interactive deep learning book with code, math, and discussions. 包含代码、数学原理和讨论的交互式深度学习书籍。 PyTorch

2. Deep Learning Theory

• Deep Learning (Ian Goodfellow et al.) The definitive textbook on deep learning. MIT Press. 深度学习领域的权威教材。 Textbook
• Understanding Deep Learning By Simon J.D. Prince. Includes slides and website, continuously updated. 作者持续更新，配套课件丰富。 Modern

3. Contrastive Predictive Coding

• DeepInfomax Tutorial on Deep Infomax and contrastive learning. 关于深度信息最大化及对比学习的教程。
• Contrastive Predictive Coding (CPC) Detailed derivation and explanation of CPC. CPC 的详细推导与解释。
• From NCE to DeepInfomax Mathematical derivations connecting Noise Contrastive Estimation to DeepInfomax. 从 NCE 到 DeepInfomax 的数学推导过程。 Math Heavy

4. AI Researcher Homepages

• Jure Leskovec Stanford University. Expert in Graph Neural Networks (GNN) and Mining. 斯坦福大学，图神经网络与挖掘专家。 GNN
• Yue Zhao Carnegie Mellon University. Focus on Anomaly Detection. 卡内基梅隆大学，专注于异常检测研究。 Anomaly Detection

5. Macroeconomics Homepages

• Christian Wolf MIT Department of Economics. 麻省理工学院经济系。
• Jesús Fernández-Villaverde University of Pennsylvania. DSGE, Heterogeneous Agent Models, Model Estimation. 宾夕法尼亚大学，研究方向包括动态随机一般均衡模型、异质性代理人模型等。 DSGE
• Frank Schorfheide University of Pennsylvania. Empirical Macroeconomics, Bayesian Model Estimation. 宾夕法尼亚大学，实证宏观经济学与贝叶斯模型估计。 Bayesian