Machine Learning

• 📚: Book | 📓: Thesis | 📃 Article
• 🗃️: Library | 🚀: Site/Blog/Profile

Awesome Heros:

• 🚀 Yi Ma: Profile
• 🚀 Radford M. Neal: Profile | Blog
• 🚀 华校专: Tutorial/Blog

https://www.yuque.com/angsweet/machine-learning

Awesome resources:

• Review

  • 📃 How to Avoid Machine Learning Pitfalls: A Guide for Academic Researchers (https://arxiv.org/abs/2108.02497)

• Books & Thesis

  • 📚《机器学习系统：设计与实现》: https://github.com/openmlsys/openmlsys-zh
    • 本开源项目试图给读者讲解现代机器学习系统的设计原理和实现经验。
  • 📓《图贝叶斯深度学习》| Bayesian Deep Learning for Graphs: https://diningphil.github.io/
  • 📚《图算法指南》| A Guide to Graph Algorithms: https://link.springer.com/book/10.1007/978-981-16-6350-5

• Blogs from experts specialized in GW/ML/DL

https://janosh.dev/

• Popular Courses

  • 国外一名工程师为 AI 开发者定制的《机器学习自学指南》，内容覆盖线性代数、多元微积分、基础机器学习、深度学习等知识。 GitHub：github.com/python-engineer/ml-study-plan
  • 【The Ultimate FREE Machine Learning Study Plan：机器学习超级免费学习计划(学习资源清单)】’The Ultimate FREE Machine Learning Study Plan’ by Patrick Loeber GitHub: https://github.com/python-engineer/ml-study-plan

• MCMC

  • Joshua S. Speagle (2019). A Conceptual Introduction to Markov Chain Monte Carlo Methods.

    PDF Cite

• Neural Likelihood Free Inference: https://neurallikelihoodfreeinference.github.io/

  • List of papers using Neural Networks for Bayesian Likelihood-Free Inference

Library

• 🗃️TorchStudio：PyTorch 及其生态专属 IDE，简单点击即可本地/远程浏览、训练和比较AI模型，可视化调试模型 | TorchStudio - IDE for PyTorch and its ecosystem: https://torchstudio.ai/
• 🗃️PyTorch/fastai 时间序列深度学习包 | Time series Timeseries Deep Learning Machine Learning Pytorch fastai: https://github.com/timeseriesAI/tsai
• 🗃️Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows (normalizing_flows): GitHub

RL:

• 🚀 RLChina 强化学习夏令营 http://rlchina.org/
• 🗃️【RLkit：强化学习算法(PyTorch)实现集】’RLkit - Collection of reinforcement learning algorithms’ by Robotic AI & Learning Lab Berkeley GitHub: https://github.com/rail-berkeley/rlkit
• 📚《深度强化学习——基础、研究与应用》《Deep Reinforcement Learning - Fundamentals, Research and Applications》: https://deepreinforcementlearningbook.org/

📃 Physics-based Deep Learning https://arxiv.org/pdf/2109.05237v1.pdf http://physicsbaseddeeplearning.org/intro.html

Math

• 📃 矩阵分解与应用 | Matrix Decomposition and Applications: https://arxiv.org/abs/2201.00145
• 🚀《机器学习：概率视角》《Machine Learning: a Probabilistic Perspective》: https://probml.github.io/pml-book/book0.html
• 🚀《概率机器学习：入门》《Probabilistic Machine Learning: An Introduction》: https://probml.github.io/pml-book/book1.html
• 🚀《概率机器学习：进阶》《Probabilistic Machine Learning: Advanced Topics》: https://probml.github.io/pml-book/book2.html