机器学习保罗万象,在学习这门技术时,最好可以有一些速查手册之类的东西在手边,它们列出了需要了解的关键点。 Robbie Allen 整理了 20 多个与机器学习相关的速查资料,并分享出来,或许也可以帮助其他学习这门技术的人。
机器学习领域正发生着日新月异的变化,这些资料总有一天会过时,不过至少在目前看来,它们仍然十分有用。如果不想一个接一个地下载这些资料,可以从这里打包下载所有的资料。
机器学习
下面是机器学习算法的一些图表,非常有用。
- 神经网络架构: http://www.asimovinstitute.org/neural-network-zoo/
- 微软 Azure 算法图表: https://docs.microsoft.com/en-us/azure/machine-learning/machine-learning-algorithm-cheat-sheet
- SAS 算法图表: http://blogs.sas.com/content/subconsciousmusings/2017/04/12/machine-learning-algorithm-use/
- 算法总结: http://machinelearningmastery.com/a-tour-of-machine-learning-algorithms/
http://thinkbigdata.in/best-known-machine-learning-algorithms-infographic/ - 算法的优劣对比: https://blog.dataiku.com/machine-learning-explained-algorithms-are-your-friend
Python
网络上有很多 Python 相关的学习课程,下面列出最好的部分资料。
- 算法: https://www.analyticsvidhya.com/blog/2015/09/full-cheatsheet-machine-learning-algorithms/
- Python 基础: http://datasciencefree.com/python.pdf
https://www.datacamp.com/community/tutorials/python-data-science-cheat-sheet-basics#gs.0x1rxEA - Numpy: https://www.dataquest.io/blog/numpy-cheat-sheet/
http://datasciencefree.com/numpy.pdf
https://www.datacamp.com/community/blog/python-numpy-cheat-sheet#gs.Nw3V6CE
https://github.com/donnemartin/data-science-ipython-notebooks/blob/master/numpy/numpy.ipynb - Pandas: http://datasciencefree.com/pandas.pdf
https://www.datacamp.com/community/blog/python-pandas-cheat-sheet#gs.S4P4T=U
https://github.com/donnemartin/data-science-ipython-notebooks/blob/master/pandas/pandas.ipynb - Matplotlib: https://www.datacamp.com/community/blog/python-matplotlib-cheat-sheet
https://github.com/donnemartin/data-science-ipython-notebooks/blob/master/matplotlib/matplotlib.ipynb - Scikit Learn: https://www.datacamp.com/community/blog/scikit-learn-cheat-sheet#gs.fZ2A1Jk
http://peekaboo-vision.blogspot.de/2013/01/machine-learning-cheat-sheet-for-scikit.html
https://github.com/rcompton/ml_cheat_sheet/blob/master/supervised_learning.ipynb - TensorFlow: https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/1_Introduction/basic_operations.ipynb
- PyTorch: https://github.com/bfortuner/pytorch-cheatsheet
数学
如果要学习机器学习,需要了解统计学、线性代数和微积分。以下的资料可以帮助你很好地了解机器学习背后的数学。
- 概率学: http://www.wzchen.com/s/probability_cheatsheet.pdf
- 线性代数: https://minireference.com/static/tutorials/linear_algebra_in_4_pages.pdf
- 统计学: http://web.mit.edu/~csvoss/Public/usabo/stats_handout.pdf
- 微积分: http://tutorial.math.lamar.edu/getfile.aspx?file=B,41,N
感谢陈思对本文的审校。
给InfoQ 中文站投稿或者参与内容翻译工作,请邮件至 editors@cn.infoq.com 。也欢迎大家通过新浪微博( @InfoQ , @丁晓昀),微信(微信号: InfoQChina )关注我们。
评论 1 条评论