信息论、推断与学习算法
Information Theory, Inference & Learning Algorithms
David J.C. MacKay · 初版 2003 年
77人推荐
93位读者提及
111次提及
为什么值得读
- 写作风格极易亲近且概念阐述清晰透彻
- 详尽覆盖了MCMC等推断算法的基础概念
- 融会贯通信息论、推断与机器学习多门学科
书封文案：本教材将理论与应用并重展开介绍。信息论与实际通信系统并肩讲授，例如用于数据压缩的算术编码和用于差错控制的稀疏图码。一套推断技术工具箱——包括消息传递算法、Monte Carlo方法和变分近似——亦随着这些工具在聚类、卷积码、独立成分分析和神经网络中的应用而逐步构建。出版方简介：本教材全面涵盖了Shannon的理
Hacker News 上怎么说
正在加载完整评论……
……朗道与栗弗席兹的理论物理学教程 - 弗拉基米尔·阿诺德关于常微分方程与经典力学的著作 - 《Winning Ways for your Mathematical Plays》（Berlekamp 等著） - 《信息论基础》（Cover & Thomas 著） - 《信息论、推理与学习算法》（MacKay 著） - 《网络优化》（Bertsekas 著） - 《凸优化》（Boyd & Vandenberghe 著） - 《非线性控制系统》（Isidori 著） - 《可视化复分析》（Needham 著） - 《激光》（Siegman 著）……
…Lifschitz's series - Vladimir Arnold's books on ODEs and Classical Mechanics - Winning Ways for your Mathematical Plays (by Berlekamp et al.) - Elements of Information Theory (by Cover & Thomas) - Information Theory, Inference, and Learning Algorithms (by MacKay) - Network Optimization (by Bertsekas) - Convex Optimization (by Boyd & Vandenberghe) - Nonlinear Control Systems (by Isidori) - Visual Complex Analysis (by Needham) - Lasers (by Siegman)…
……多元微积分、线性代数、概率论和信息论的基础。熟悉图论也会很有帮助。在我看来，最好的入门起点之一是 David MacKay 写的《信息论、推理与学习算法》。虽然这书现在有点年头了，但它依然是该领域最平易近人、写得最好的书之一。另一本经得起时间考验的老书是《概率论：……
…grounding in multi-variable calculus, linear algebra, probability theory and information theory. It will also be helpful to be well versed in graph theory. In my opinion one of the best starting points is "Information Theory, Inference and Learning Algorithms" by David MacKaye. It's a bit long in the tooth now, but it is still one of the most approachable and well written books in the field. Another old book that stands up very well is "Probability Theory:…
……《Practical Common LISP》 - Seibel 《Programming Perl》 - Wall, Christiansen 和 Orwant 《ANSI Common Lisp》 - Graham 《重构》 - Fowler 《UML 精粹》 - Fowler 《计算理论导引》 - Sipser 《信息论、推理与学习算法》 - MacKay 《现代操作系统》 - Tanenbaum 《On Lisp》 - Graham 《黑客与画家》 - Graham 《人工智能编程范式》 - Norvig 《模式识别与机器学习》 - Bishop 《Java……
…Practical Common LISP - Seibel Programming Perl - Wall, Christiansen and Orwant ANSI Common Lisp - Graham Refactoring - Fowler UML Distilled - Fowler Introduction to the Theory of Computation - Sisper Information Theory, Inference, and Learning Algorithms - MacKay Modern Operating Systems - Tanenbaum On Lisp - Graham Hackers & Painters - Graham Paradigms of Artificial Intelligence - Norvig Pattern Recognition and Machine Learning - Bishop The Java…
David MacKay 在他那本内容详尽的大部头《信息论、推理与学习算法》里讲了 MCMC，这里可以免费获取：http://www.inference.phy.cam.ac.uk/itprnn/book.html 这些内容在接近书末的位置。足够让你熟悉并理解基本概念了……
David Mackay covers MCMC in his exhaustive book titled "Information Theory, Inference, and Learning Algorithms" available for free here: http://www.inference.phy.cam.ac.uk/itprnn/book.html They are covered near the end of the book. It should be enough to familarize yourself with and understand the basic concepts…
我也赞同这点。这大概是我心目中仅次于 MacKay 的《信息论、推理与学习算法》的教科书了。如果你肯花时间踏踏实实跟着书学一遍，你对凸优化的理论和方法都会有一个非常棒的理解。
i second this. this is probably my favorite text book behind Mackay's "Information Theory, Inference, and Learning Algorithms". if you take the time to honestly follow the text you come away with a great understanding of convex optimization... both the theory and the methods.
……配合加州理工的视频课程一起看：http://work.caltech.edu/telecourse.html Bishop 的《模式识别与机器学习》http://research.microsoft.com/en-us/um/people/cmbishop/prml/ 同样值得关注的还有 MacKay 的《信息论、推理与学习算法》，免费：http://www.inference.phy.cam.ac.uk/itprnn/book.html van der Heijden 的《分类、参数估计与状态估计》http://prtools.org 《计算机视觉：模型、学习……
…with Caltech video lectures: http://work.caltech.edu/telecourse.html Pattern Recognition and Machine Learning, by Bischop http://research.microsoft.com/en-us/um/people/cmbishop/prml/ Also noteworthy Information Theory, Inference, and Learning Algorithms, by Mackay, free. http://www.inference.phy.cam.ac.uk/itprnn/book.html Classification, Parameter Estimation and State Estimation, by van der Heijden. http://prtools.org Computer Vision: Models, Learning,…