AI 与机器学习cs.huji.ac.il编辑精选
《理解机器学习:从理论到算法》免费书
Understanding Machine Learning: From Theory to Algorithms
2015 — 2025,它一次次回到首页
黑点是上首页(≥ 50 分)的那次投稿,空心点是没冲上去的投稿,点越大分数越高。
导读
这个页面围绕《Understanding Machine Learning: From Theory to Algorithms》这本机器学习教材,内容从学习理论的基础讲到具体算法,风格数学严谨而简洁。它适合想弄懂机器学习背后原理、而不满足于只调用现成工具的读者。
为什么经久不衰:它把学习理论与具体算法连成一条线,数学密集但务实精炼,因此多年后仍是打牢机器学习原理基础的经典读物。
HN 评论精选
推荐《统计学习基础》作为更深入的补充,强调投入时间值得,前几章也有很大收获。
我是数学爱好者,也是主要靠自学的数据科学家。《统计学习基础》(The Elements of Statistical Learning)是我见过最好的书。我花了几百小时才读完,但如果你想深入理解,绝对值得。哪怕只读到第3章,你也会比大多数人懂得多,并打下很好的基础。希望对你有帮助!
arbitrage314查看英文原文
I'm a math geek, but I'm also a mostly self-taught data scientist. "The Elements of Statistical Learning" (https://web.stanford.edu/~hastie/local.ftp/Springer/OLD/ESLII_print4.pdf) is far and away the best book I've seen. It took me hundreds of hours to get through it, but if you're looking to understand things at a pretty deep level, I'd say it's well-worth it. Even if you stop at chapter 3, you'll still know more than most people, and you'll have a great foundation. Hope this helps!
指出作者与 Pegasos 的关联,说明书中的理论有简洁实用的算法对应。
出于好奇:作者之一还提出了 Pegasos SVM,这是一种很好的 SVM 在线近似,大约 15 行代码就能写出来。
pmelendez查看英文原文
Just a curiosity: One of the authors also proposed Pegasos SVM [1] which is a nice online approximation to SVM and that can be written in 15 lines of code or so. http://ttic.uchicago.edu/~nati/Publications/PegasosMPB.pdf
批评教材和教程数学门槛过高,与普通开发者的实用需求脱节。
我觉得机器学习对我的门槛——正如许多教程和书里那样,一上来就甩出大量数学——是直接的劝退。我们很多人不是刚毕业,需要戴眼镜,晚上八点孩子睡了就在沙发上睡着……数学是埋在多年非数学事物下的遥远记忆碎片。感觉机器学习只由学术界教授,但很多受众是想马上上手玩一玩的普通开发者。
cdnsteve查看英文原文
I feel like the barrier to machine learning for me, as I've seen in many tutorials and books and is an immediate discouragement, is the massive amount of math thrown in your face. Many of us didn't just graduate, need glasses and fall asleep at 8pm on the couch when the kids are in bed... Math is this distant fragment of memory buried under years of everything not Math. It feels like machine learning is only taught by academia but the majority of the audience is for practical use by the average developer wanting to play with it today.
读者评价:务实、精炼、数学密集,重点不在神经网络,习题有难度。
我读过这本书,强烈推荐。它有一种非常务实、不废话的风格,数学性强且简洁。神经网络那一章很短(不过没关系,那不是重点),有些习题真的很难,但总体上我很喜欢。
inglor查看英文原文
I've read this book and warmly recommend it. It has a very pragmatic "no bullshit" approach and it's very mathematical and concise. The neural networks chapter is tiny (but that's ok - that's not the focus) and some of the questions are really hard - but overall I've really enjoyed it.
历次讨论
同类还值得读
如何写一个拼写纠正器
How to Write a Spelling Corrector
Peter Norvig 用一个几十行的 Python 程序演示如何做拼写纠正:先用编辑距离(删除、插入、替换、换位)生成所有可能的候选词,再用从大量文本中统计出的词频概率,选出…
AI 与机器学习上首页 10 次 · 2007–2022norvig.com编辑精选面向黑客的概率编程与贝叶斯方法
Probabilistic Programming and Bayesian Methods for Hackers (2013)
《黑客的贝叶斯方法与概率编程》是一本开源的贝叶斯统计入门书,以 Python/PyMC 代码和交互式 Jupyter Notebook 为主线,强调“先实践、后数学”的学习路径,…
AI 与机器学习上首页 5 次 · 2013–2018camdavidsonpilon.github.io编辑精选神经网络黑客指南
Hacker's Guide to Neural Networks
Andrej Karpathy 写的神经网络入门教程,面向程序员,从最简单的表达式求导讲起,逐步推导出反向传播和梯度下降,最后引出神经网络。
AI 与机器学习上首页 4 次 · 2014–2019karpathy.github.io编辑精选神经网络能逼近任意函数的可视化证明
A visual proof that neural nets can approximate any function
这一章来自 Michael Nielsen 的在线书《Neural Networks and Deep Learning》,用 sigmoid 单元叠加成局部隆起/平滑阶跃的图示…
AI 与机器学习上首页 4 次 · 2014–2022neuralnetworksanddeeplearning.com编辑精选论乔姆斯基与统计学习的两种文化
On Chomsky and the Two Cultures of Statistical Learning
Norvig 回应 Chomsky 对统计语言模型批评的文章,围绕“统计学习能否解释语言”展开,比较生成与解释、少参数模型与 Shannon 式高参数统计模型。
AI 与机器学习上首页 4 次 · 2011–2025norvig.com编辑精选