“My current favorite, Information Theory Inference and Learning Algorithms, available online for free.:)”
David MacKay 把信息论、编码、贝叶斯推断和神经网络放进同一本书,讲清它们在概率视角下如何互相联系。书中穿插大量习题和个人风格浓厚的讲解,不是干巴巴的定理堆砌。和只讲机器学习算法的教材相比,它更强调概率与压缩的统一视角。作者提供免费 PDF,甚至放出了 LaTeX 源文件。
HN 上的人把它当作免费、好读又严谨的教材反复推荐,不少人称它是自己最喜欢的书;也有人说它能让人少一点遇到数据就套神经网络的习惯,并看到机器学习、信息论和统计如何统一起来。
想从概率与信息视角理解机器学习的自学者
怎么读
由 Claude 根据这本书和 HN 上的说法整理,可能有错- 1先读信息论和概率的开头几章,再决定要不要读后面的编码部分
- 2对机器学习感兴趣的读者,可以直接跳到推断和神经网络相关章节
- 3认真做书中的习题,作者的提示和评注很有价值
- 4配合作者公开的讲课视频一起看,更容易跟上
HN 书评
推荐在前,同类按时间 · 每本最多保留 20 条,统计用全部提及 · 作者本人贴的不算“By far my favorite book on the subject is conveniently available for free on the internet!”
“David MacKay wrote a good intro book on Bayesian, neural networks, and related topics: Information Theory, Inference, and Learning Algorithms”
“Information Theory, Inference and Learning Algorithms by David MacKay is excellent, and freely available online.”
“For more details, you might start with:”
“Book recommendation: David MacKay's (free) book”
看全部 20 条 →
“same great clarity of explanation”
“May I also recommend a related book, also a free PDF:”
“it was Information Theory, Inference, and Learning Algorithms that sparked off a lot of study”
“More gentle introduction in this (free to download) text book:”
“see Wiki or David MacKay's wonderful book for details.”
“And last, but certainly not least:”
“here are some good online resources for machine learning:”
“excellent and free book BTW”
“I would add to that two classics with free PDFs available from the authors' websites:”
“for folks looking to delve into the subject, Barber and McKay's freely available content books are terrific”
“And yet another is David Mackay, who taught me at undergrad:”
“You could look at the appendixes in texts by Bishop, MacKay, Barber and Rasmussen/Williams to see what they expect”
“Here are a few tangentially related things that may be of interest:”
“If you have time, I'd also read something like David Mackay's information theory textbook [1] for more of a Bayesian perspective.”