机器学习参考资料:
机器学习参考书籍:
- 《神经网络与深度学习》书籍及PPT:https://nndl.github.io/
- 《统计学习方法》李航著
- 《机器学习》周志华著
- 《南瓜书》:https://datawhalechina.github.io/pumpkin-book/, https://github.com/datawhalechina/pumpkin-book
- 《迁移学习》杨强等著
- 《联邦学习》杨强等著
- Python Machine Learning: https://github.com/rasbt/python-machine-learning-book
- 深度学习:英文版( https://www.deeplearningbook.org/)、中文版( https://github.com/exacity/deeplearningbook-chinese)
- 《强化学习Reinforcement Learning(第2版)》[加]Richard S.Sutton [美]Andrew G. Barto著,俞凯等译
数学类参考书籍:
- 凸优化Convex Optimization(http://stanford.edu/~boyd/cvxbook/)、
- 线性代数 https://ocw.mit.edu/courses/mathematics/18-06sc-linear-algebra-fall-2011/index.htm
- 概率论与统计:1)斯坦福课程CS109 Probability for Computer Scientists: http://web.stanford.edu/class/cs109/;2)Introduction to Probability, Statistics, and Random Processes: https://www.probabilitycourse.com/
机器学习库/平台:
- SKlearn(https://scikit-learn.org/stable/),SKlearn的User Guide里总结了很多机器学习模型,可以学习下https://scikit-learn.org/stable/user_guide.html。上面提到的Python Machine Learning书籍中就大量使用SKlearn的API。
- Pytorch: https://pytorch.org/tutorials/
- TensorFlow
- Keras( https://keras.io/)等。
线上课程:
- 吴恩达教授的视频教学课程( https://www.coursera.org/learn/machine-learning)
- 李宏毅-台湾大学(http://speech.ee.ntu.edu.tw/~tlkagk/courses_ML20.html)
- Google的深度学习课程(https://www.udacity.com/course/intro-to-tensorflow-for-deep-learning--ud187)
- 李飞飞教授的计算机视觉课程(http://cs231n.stanford.edu)
- Richard Socher 的自然语言处理课程(http://cs224d.stanford.edu)
- University of Chicago Mathematical Foundations of Machine Learning(https://voices.uchicago.edu/willett/teaching/mathematical-foundations-of-machine-learning-fall-2020/)
其他资料:
- Machine Learning and Artificial Intelligence and their role in networking: https://www.bilibili.com/video/av70398058/
- 链接:https://pan.baidu.com/s/1qgYRbtfCLZE8d0MuCSrRLw 密码:1am4
- 链接:https://pan.baidu.com/s/1YAujUyivMKZcOCUxB9GZlw 提取码:wru7
声明: 内容摘自王老师的个人主页。