1.Andrew Moore. The dean of Carnegie Mellon Computer College is big. These basically cover a lot of data mining topic.
Decision Trees Information Gain probability for Data miners probability Density Functions Gaussians Maximum likelihood Es Timation Gaussian Bayes classifiers cross-validation Neural Networks instance-based Learning (aka case-based or Memory-bas Ed or non-parametric) Eight Regression algorithms predicting real-valued outputs:an Introduction to Regression Bayesian N Etworks Inference in Bayesian Networks (by Scott Davies and Andrew Moore) learning Bayesian Networks A short Intro to Naiv E Bayesian classifiers Short overview of Bayes Nets Gaussian Mixture Models K-means and hierarchical clustering Hidden Mar Kov Models VC Dimension support Vector Machines PAC Learning Markov decision Processes Reinforcement Learning Biosurveilla Nce:an example Elementary probability and Naive Bayes classifiers Spatial surveillance time Series Methods Game Tree Sear CH algorithms, including Alpha-beta Search zero-sum game theory Non-zero-sum game Theory Introductory Overview of Time-ser Ies-based Anomaly DetectIon algorithms AI Class Introduction search algorithms A-star heuristic search Constraint satisfaction algorithms with AP Plications in computer Vision and scheduling Robot Motion planning hillclimbing, simulated annealing and genetic algorithm S 2.
Stanford University opened a course on "deep learning and natural language processing" in March: Cs224d:deep Learning for Natural Language processing, the instructor is young talent Richard Socher, he himself is a German, During his time at the university, he was involved in natural language processing, studied computer vision in Germany, and then studied at Stanford University, where he was studying for a doctorate, a PhD in the field of Master NLP in the field of Manning and the deep learning, Andrew Ng, whose doctoral thesis was Recursive Deep Learning for Natural Language processing and computer Vision is also a perfect hit for years of schooling. After graduating as co-founder and CTO of the identity of the founding of Metamind, as the AI in the field of new star start-up company, Metamind was founded at the beginning of the 8 million-dollar venture, it deserves attention.
Back to the course, cs224d can be translated as "deep learning for Natural language processing (Deepin learning for Natural Language processing)", which is an on-campus course for Stanford students, However, the relevant material of the course is put on the net, including course video, courseware, related knowledge, preparation knowledge, homework and so on, quite complete. The syllabus is quite methodical and depth, starting with the basics, and then talking about the specific applications of deep learning in the NLP domain, including named entity recognition, machine translation, syntactic analyzers, affective analysis, and so on. Richard Socher had previously done a tutorial,deep learning for NLP (without Magic) in ACL 2012 and Naacl 2013, and interested students could refer first: deep learning for N LP (without Magic) –acl tutorial– related videos and courseware. In addition, due to this course of video on YouTube, @ Love Coco-love life teacher maintained a network disk link: Http://pan.baidu.com/s/1pJyrXaF, synchronization update related information, can be concerned about.
Course Homepage Link http://cs224d.stanford.edu/syllabus.html
Event |
Date |
Description |
Course Materials |
Lecture |
Mar 30 |
Intro to NLP and deep learning |
Suggested Readings: [Linear Algebra Review] [probability Review] [convex optimization Review] [more Optimization (SGD) Rev Iew] [from Frequency to Meaning:vector Space Models of semantics] [lecture Notes 1] [Python tutorial] [Slides] [VIDEO] |
Lecture |
APR 1 |
Simple Word Vector Representations:word2vec, GloVe |
Suggested readings: [Distributed representations of Words and phrases and their compositionality] [efficient Estimation of Word representations in Vector Space] [slides] [VIDEO] |
Lecture |
APR 6 |
Advanced Word vector representations:language models, Softmax, single layer networks |
Suggested Readings: [Glove:global Vectors for Word representation] [improving word representations via Global Context and Multiple Word prototypes] [lecture Notes 2] [Slides] [VIDEO] |
Lecture |
APR 8 |
Neural Networks and BackPropagation--for named entity recognition |
Suggested Readings: [UFLDL Tutorial] [Learning Representations by backpropogating Errors] [slides] [VIDEO] |
Lecture |
APR 13 |
Project Advice, Neural Networks and Back-prop (in full gory detail) |
Suggested Readings: [Natural Language Processing (almost) from Scratch] [A neural Network for Factoid Question answering O ver paragraphs] [grounded compositional semantics for finding and describing Images with sentences] [deep visual-semantic Alignments for generating Image descriptions] [Recursive deep Models for Semantic compositionality over a sentiment Treeba NK] [(NEW) lecture Notes 3] [Slides] [VIDEO] |
Lecture |
APR 15 |
Practical tips:gradient checks, overfitting, regularization, activation functions, details |
Suggested Readings: [Practical recommendations for gradient-based training of deep architectures] [UFLDL page on gradient Checking] [slides] [VIDEO] |
A1 Due |
APR 16 |
Assignment #1 Due |
[Pset 1] |
Lecture |
APR 20 |
Recurrent neural networks--for language modeling and other tasks |
Suggested readings: [Recurrent neural network based language model] [Extensions of recurrent neural network language model ] [Opinion Mining with deep recurrent neural Networks] [(NEW) lecture Notes 4] [Slides] [VIDEO] [Minimal net example (Karpathy)] [Vanishing Grad Example] [Vanishing Grad Notebook] |
Proposal due |
APR 21 |
Course Project proposal Due |
[Proposal Description] |
Lecture |
APR 22 |
Grus and Lstms--for machine translation |
Suggested readings: [Long short-term Memory] [Gated Feedback recurrent neural Networks] [empirical Evaluation of Gated Rec Urrent neural Networks on Sequence Modeling] [slides] [VIDEO] |
Lecture |
APR 27 |
Recursive Neural Networks--for parsing |
Suggested readings: [Parsing with compositional Vector grammars] [subgradient Methods for structured prediction] [Parsing Natural Scenes and Natural Language with Recursive neural Networks] [slides] [VIDEO] |
Lecture |
APR 29 |
Recursive Neural Networks--for different tasks (e.g. sentiment analysis) |
Suggested readings: [Recursive deep Models for Semantic compositionality over a sentiment treebank] [Dynamic Pooling and U Nfolding Recursive autoencoders for paraphrase Detection] [improved Semantic representations from tree-structured Long Sho Rt-term Memory Networks] [slides] [VIDEO] |
|
A2 Due |
APR 30 |
Pset #2 Due Date |
[Pset #2] |
Lecture |
May 4 |
Review Session for midterm |
Suggested readings:n/a [slides] [Video-see Piazza] |
Midterm |
May 6 |
In-class Midterm |
&n |