UCB CS189/289A: Introduction to Machine Learning

课程简介

• 先修要求：微积分，线性代数，概率论，算法，Python，一些基础的矩阵求导知识
• 参考材料：Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, and Jerome Friedman
• 主要内容：Theoretical foundations, algorithms, methodologies, and applications for machine learning. Topics include supervised methods for regression and classication (linear models, trees, neural networks, ensemble methods, instance-based methods); generative and discriminative probabilistic models; deep learning models including CNNs, Transformers, graph neural networks for vision and language tasks; and Markovian models for reinforcement learning and robotics.

个人心得

我在学习完 CS229 之后利用这门课进行了知识点的补充。同 CS229 一样，这门课也有非常详尽的 notes 可供阅读，并且还对外公布了所有课程作业和解答，非常适合用于和 CS229 结合起来学习，口感甚佳。

相关链接

1. 课程网站：https://eecs189.org/
2. 课程视频：B 站，Youtube
3. 课程教材：Elements of Statistical Learning