推荐｜约翰霍普金斯大学计算机科学系Jason Eisner教授总结了一系列的自然语言处理优秀教学资源

>>>>>>欢迎投稿：[e-mail]<<<<<<

全球人工智能

下面是约翰霍普金斯大学计算机科学系Jason Eisner教授总结的一系列的自然语言处理优秀教学资源，希望对大家有用：

• The difference between natural language processing (NLP) and computational linguistics (CL)

  http://www.quora.com/What-is-the-difference-between-natural-language-processing-and-computational-linguistics/answer/Jason-Eisner?share=1

• The difference between AI, ML, and NLP

  http://www.quora.com/Whats-the-difference-between-Machine-Learning-AI-and-NLP/answer/Jason-Eisner?share=1

• The difference between frequentists and Bayesians: A dialogue

  http://www.quora.com/For-a-non-expert-what-is-the-difference-between-Bayesian-and-frequentist-approaches/answer/Jason-Eisner?share=1

• The three cultures of machine learning

  https://www.cs.jhu.edu/~jason/tutorials/ml-simplex.html

• Probability crash course (+) — how to build simple probabilistic models

  http://videolectures.net/hltss2010_eisner_plm/video/1/

• Interactive lessons in  — nifty visualization toy with sliders

• Latent-variable log-linear modeling

  http://www.quora.com/What-is-the-latent-log-linear-model-with-latent-variables-and-how-do-you-train-such-a-model/answer/Jason-Eisner?share=1

• Interactive visualization of kernel SVMs (by Guillaume Caron: I'm only hosting it

  https://www.cs.jhu.edu/~jason/tutorials/SVMApplet/

• Lagrange multipliers — high-level explanation

  http://www.umiacs.umd.edu/~resnik/ling848_fa2004/lagrange.html

• Variational inference — high-level explanation

  https://www.cs.jhu.edu/~jason/tutorials/variational.html

• Belief propagation (slides) — high-level explanation; ACL 2014/2015 tutorial

  https://www.cs.jhu.edu/~jason/tutorials/bp.ppt

  http://www.cs.jhu.edu/~mrg/bp-tutorial/

• Hidden Markov Models (video+more) — a fun detailed example

  https://www.cs.jhu.edu/~jason/papers/#eisner-2002-tnlp

• Back-propagation (animated slides+video) — high-level explanation; also see suggested readings at top of 

  https://www.cs.jhu.edu/~jason/tutorials/backprop-pool.pptx

• Understanding the inside-outside and forward-backward algorithms -- they're just backprop

  http://cs.jhu.edu/~jason/papers/#spnlp16

• An annotated drawing of an LSTM unit (based on Graves 2012)

  https://www.cs.jhu.edu/~jason/tutorials/lstm.png

  https://www.cs.toronto.edu/~graves/preprint.pdf

• Bayesian generative modeling (video+) — works up to topic models and Bayesian HMMs

  http://techtalks.tv/events/76/?page=2

• Minimum spanning tree (tutorial paper) — deep and clear coverage of how 7 algorithms were designed

  http://cs.jhu.edu/~jason/papers/#eisner-1997-mst

• Convert a formula from SAT to CNF-SAT (pseudocode and discussion)

  https://www.cs.jhu.edu/~jason/tutorials/convert-to-CNF.html

• Competitive grammar writing exercise, with software

  https://www.cs.jhu.edu/~jason/papers/#smith-eisner-2008-cgw

热门文章推荐