Category Archives: Class

[open class ] Natural Language processing Video Lectures

original:https://class.coursera.org/nlp/lecture/preview

Video Lectures

Week 1 – Course Introduction

(expanded, click to collapse)

Week 1 – Basic Text Processing

(expanded, click to collapse)

Week 1 – Edit Distance

(expanded, click to collapse)

Week 2 – Language Modeling

(expanded, click to collapse)

Week 2 – Spelling Correction

(expanded, click to collapse)

Week 3 – Text Classification

(expanded, click to collapse)

Week 3 – Sentiment Analysis

(expanded, click to collapse)

Week 4 – Discriminative classifiers: Maximum Entropy classifiers

(expanded, click to collapse)

Week 4 – Named entity recognition and Maximum Entropy Sequence Models

(expanded, click to collapse)

Week 4 – Relation Extraction

(expanded, click to collapse)

Week 5 – Advanced Maximum Entropy Models

(expanded, click to collapse)

Week 5 – POS Tagging

(expanded, click to collapse)

Week 5 – Parsing Introduction

(expanded, click to collapse)

Week 5 – Instructor Chat

(expanded, click to collapse)

Week 6 – Probabilistic Parsing

(expanded, click to collapse)

Week 6 – Lexicalized Parsing

(expanded, click to collapse)

Week 6 – Dependency Parsing (Optional)

(expanded, click to collapse)

Week 7 – Information Retrieval

(expanded, click to collapse)

Week 7 – Ranked Information Retrieval

(expanded, click to collapse)

 

[open class ] Download Video Lectures

original:http://www.ml-class.org/course/video/list?mode=download

Download Video Lectures

I. INTRODUCTION
II. LINEAR REGRESSION WITH ONE VARIABLE
III. LINEAR ALGEBRA REVIEW (OPTIONAL)
IV. LINEAR REGRESSION WITH MULTIPLE VARIABLES
V. OCTAVE TUTORIAL
VI. LOGISTIC REGRESSION
VII. REGULARIZATION
VIII. NEURAL NETWORKS: REPRESENTATION
IX. NEURAL NETWORKS: LEARNING
X. ADVICE FOR APPLYING MACHINE LEARNING
XI. MACHINE LEARNING SYSTEM DESIGN
XII. SUPPORT VECTOR MACHINES
XIII. CLUSTERING
XIV. DIMENSIONALITY REDUCTION
XV. ANOMALY DETECTION
XVI. RECOMMENDER SYSTEMS
XVII. LARGE SCALE MACHINE LEARNING
XVIII. APPLICATION EXAMPLE: PHOTO OCR
XIX. CONCLUSION

[open class ] Lecture Slides

original:http://www.ml-class.org/course/resources/index?page=course-materials

Introduction to Machine Learning
Annotated slides
PDF slides
Linear regression with one variable
Annotated slides
PDF slides
Linear algebra review
Annotated slides
PDF slides
Linear regression with multiple variables
Annotated slides
PDF slides
Octave Tutorial
Octave Notes
Logistic regression
Annotated slides
PDF slides
Regularization
Annotated slides
PDF slides
Neural Networks: Representation
Annotated slides
PDF slides
Neural Networks: Learning
Annotated slides
PDF slides
Advice for Applying Machine Learning
Annotated slides
PDF slides
Machine Learning System Design
Annotated slides
PDF slides
Support Vector Machines
Annotated slides
PDF slides
Clustering
Annotated slides
PDF slides
Dimensionality Reduction
Annotated slides
PDF slides
Anomaly Detection
Annotated slides
PDF slides
Recommender Systems
Annotated slides
PDF slides
Learning with Large Datasets
Annotated slides
PDF slides
Application Example: Photo OCR
Annotated slides
PDF slides

[open class ] Video Lectures

original:http://www.ml-class.org/course/video/list

View Video Lectures

I. INTRODUCTION
II. LINEAR REGRESSION WITH ONE VARIABLE
III. LINEAR ALGEBRA REVIEW (OPTIONAL)
IV. LINEAR REGRESSION WITH MULTIPLE VARIABLES
V. OCTAVE TUTORIAL
VI. LOGISTIC REGRESSION
VII. REGULARIZATION
VIII. NEURAL NETWORKS: REPRESENTATION
IX. NEURAL NETWORKS: LEARNING
X. ADVICE FOR APPLYING MACHINE LEARNING
XI. MACHINE LEARNING SYSTEM DESIGN
XII. SUPPORT VECTOR MACHINES
XIII. CLUSTERING
XIV. DIMENSIONALITY REDUCTION
XV. ANOMALY DETECTION
XVI. RECOMMENDER SYSTEMS
XVII. LARGE SCALE MACHINE LEARNING
XVIII. APPLICATION EXAMPLE: PHOTO OCR
XIX. CONCLUSION

[Online Education ]Design and Analysis of Algorithms I

original:http://www.algo-class.org/

About The Course

In this course you will learn several fundamental principles of algorithm design. You’ll learn the divide-and-conquer design paradigm, with applications to fast sorting, searching, and multiplication. You’ll learn several blazingly fast primitives for computing on graphs, such as how to compute connectivity information and shortest paths. Finally, we’ll study how allowing the computer to “flip coins” can lead to elegant and practical algorithms and data structures. Learn the answers to questions such as: How do data structures like heaps, hash tables, bloom filters, and balanced search trees actually work, anyway? How come QuickSort runs so fast? What can graph algorithms tell us about the structure of the Web and social networks? Did my 3rd-grade teacher explain only a suboptimal algorithm for multiplying two numbers?

Prerequisites

How to program in at least one programming language (like C, Java, or Python); familiarity with proofs, including proofs by induction and by contradiction; and some discrete probability, like how to compute the probability that a poker hand is a full house. At Stanford, a version of this course is taken by sophomore, junior, and senior-level computer science majors.

Textbooks

No books are required for the course. However, three books have significantly influenced the instructor’s presentation and can be consulted for extra details. In order of decreasing relevance to the course, they are: Kleinberg & TardosAlgorithm Design, Dasgupta, Papadimitriou & VaziraniAlgorithms, and Cormen, Leiserson, Rivest, & SteinIntroduction to Algorithms.

No special software (e.g., development enviroment) is required to take this course.

The Instructor

Tim Roughgarden is an Associate Professor of Computer Science and (by courtesy) Management Science and Enginering at Stanford University, where he holds the Chambers Faculty Scholar development chair. At Stanford, he has taught the Design and Analysis of Algorithms course for the past eight years. His research concerns the theory and applications of algorithms, especially for networks, auctions and other game-theoretic applications, and data privacy. For his research, he has been awarded the ACM Grace Murray Hopper Award, the Presidential Early Career Award for Scientists and Engineers (PECASE), the Shapley Lecturership of the Game Theory Society, a Sloan Fellowship, INFORM’s Optimization Prize for Young Researchers, and the Mathematical Programming Society’s Tucker Prize.

Frequently Asked Questions

  1. When does the class start?The class will start in January 2012.
  2. What is the format of the class?The class will consist of lecture videos, which are broken into small chunks, usually between eight and twelve minutes each. Some of these may contain integrated quiz questions. There will also be standalone quizzes that are not part of video lectures, and programming assignments. There will be approximately two hours worth of video content per week.
  3. Will the text of the lectures be available?We hope to transcribe the lectures into text to make them more accessible for those not fluent in English. Stay tuned.
  4. Do I need to watch the lectures live?No. You can watch the lectures at your leisure.
  5. Can online students ask questions and/or contact the professor?Yes, but not directly There is a Q&A forum in which students rank questions and answers, so that the most important questions and the best answers bubble to the top. Teaching staff will monitor these forums, so that important questions not answered by other students can be addressed.
  6. Will other Stanford resources be available to online students?No.

 

[Online Education ]Information Theory

original:http://www.infotheory-class.org/

About The Course

Information theory is the science of operations on data such as compression, storage, and communication. It is among the few disciplines fortunate to have a precise date of birth: 1948, with the publication of Claude E. Shannon’s paper entitled “A Mathematical Theory of Communication”.

Our course will explore the basic concepts of Information theory. It is a prerequisite for research in this area, and highly recommended for students planning to delve into the fields of communications, data compression, and statistical signal processing. The intimate acquaintance that we will gain with measures of information and uncertainty – such as mutual information, entropy, and relative entropy – would be invaluable also for students, researchers, and practitioners in fields ranging from neuroscience to machine learning. Also encouraged to enroll are students of statistics and probability, who will gain an appreciation for the interplay between information theory, combinatorics, probability, and statistics.

Prerequisites

A solid first (undergraduate) course in probability, as well as the maturity and motivation to cope with some concepts that may be more abstract than you have previously encountered.

Textbooks

The lectures will be self contained and cover all the material that students are expected to know for the homework (weekly exercises) and the exams (midterm and final). A course reader will also be made available (for free). It contains an outline of the lectures, as well as pointers to references that can be consulted for further reading. These pointers are primarily to the textbooks of Cover & Thomas, Gallager, and Csiszár & Körner.

Instructor

Tsachy Weissman joined the faculty at Stanford University in 2003, where he now holds the STMicroelectronics Chair in the School of Engineering. His research focuses on Information Theory, Statistical Signal Processing, the interplay between them, and their applications. He is inventor of several patents and involved in a number of high-tech companies as member of the technical board. Among his recent awards and honors are an NSF CAREER, a joint Information-Theory/Communication societies best paper award, a Horev fellowship for Leaders in Science and Technology, and a Henry Taub prize for excellence in research. He is on the editorial board of the IEEE Transactions on Information Theory, serving as Associate Editor for Shannon Theory.

Frequently Asked Questions

  1. When does the class start?The class will start in March 2012.
  2. What is the format of the class?The class will consist of lecture videos, which are broken into small chunks, usually between eight and twelve minutes each. Some of these may contain integrated quiz questions. There will also be standalone quizzes that are not part of video lectures. There will be approximately two hours worth of video content per week.
  3. Will the text of the lectures be available?We hope to transcribe the lectures into text to make them more accessible for those not fluent in English. Stay tuned.
  4. Do I need to watch the lectures live?No. You can watch the lectures at your leisure.
  5. Can online students ask questions and/or contact the professor?Yes, but not directly. There is a Q&A forum in which students rank questions and answers, so that the most important questions and the best answers bubble to the top. Teaching staff will monitor these forums, so that important questions not answered by other students can be addressed.
  6. Will other Stanford resources be available to online students?No.

 

[Online Education ]Cryptography

original:http://www.crypto-class.org/

About The Course

Cryptography is an indispensable tool for protecting information in computer systems. This course explains the inner workings of cryptographic primitives and how to correctly use them. Students will learn how to reason about the security of cryptographic constructions and how to apply this knowledge to real-world applications. The course begins with a detailed discussion of how two parties who have a shared secret key can communicate securely when a powerful adversary eavesdrops and tampers with traffic. We will examine many deployed protocols and analyze mistakes in existing systems. The second half of the course discusses public-key techniques that let two or more parties generate a shared secret key. We will cover the relevant number theory and discuss public-key encryption, digital signatures, and authentication protocols. Towards the end of the course we will cover more advanced topics such as zero-knowledge, distributed protocols such as secure auctions, and a number of privacy mechanisms. Throughout the course students will be exposed to many exciting open problems in the field.

The course will include written homeworks and programming labs. The course is self-contained, however it will be helpful to have a basic understanding of discrete probability theory.

The Instructor

Professor Dan Boneh heads the applied cryptography group at the Computer Science department at Stanford University. Professor Boneh’s research focuses on applications of cryptography to computer security. His work includes cryptosystems with novel properties, web security, security for mobile devices, digital copyright protection, and cryptanalysis. He is the author of over a hundred publications in the field and a recipient of the Packard Award, the Alfred P. Sloan Award, and the RSA award in mathematics. Last year Dr. Boneh received the Ishii award for industry education innovation. Professor Boneh received his Ph.D from Princeton University and joined Stanford in 1997.

Frequently Asked Questions

  1. When does the class start?The class will start in January 2012.
  2. What is the format of the class?The class will consist of lecture videos, which are broken into small chunks, usually between eight and twelve minutes each. Some of these may contain integrated quiz questions. There will also be standalone quizzes that are not part of video lectures, and programming assignments. There will be approximately two hours worth of video content per week.
  3. Will the text of the lectures be available?We hope to transcribe the lectures into text to make them more accessible for those not fluent in English. Stay tuned.
  4. Do I need to watch the lectures live?No. You can watch the lectures at your leisure.
  5. Can online students ask questions and/or contact the professor?Yes, but not directly There is a Q&A forum in which students rank questions and answers, so that the most important questions and the best answers bubble to the top. Teaching staff will monitor these forums, so that important questions not answered by other students can be addressed.
  6. Will other Stanford resources be available to online students?No.
  7. How much programming background is needed for the course?The course includes programming assignments and some programming background will be helpful. However, we will hand out lots of starter code that will help students complete the assignments. We will also point to online resources that can help students find the necessary background.
  8. What math background is needed for the course?The course is mostly self contained, however some knowledge of discrete probability will be helpful. Thewikibooks article on discrete probability should give sufficient background.