Probabilistic Graphical Models 2: Inference

Probabilistic graphical models (PGMs) are a rich framework for encoding probability distributions over complex domains: joint (multivariate) distributions over large numbers of random variables that interact with each other. These representations sit at the intersection of statistics and computer science, relying on concepts from probability theory, graph algorithms, machine learning, and more. They are the basis for the state-of-the-art methods in a wide variety of applications, such as medical diagnosis, image understanding, speech recognition, natural language processing, and many, many mor

( 57 Reviews )

Created by: Daphne Koller

Quality Score

Content Quality

Video Quality

Qualified Instructor

Course Pace

Course Depth & Coverage

Overall Score : 84 / 100

Course Description

Probabilistic graphical models (PGMs) are a rich framework for encoding probability distributions over complex domains: joint (multivariate) distributions over large numbers of random variables that interact with each other. These representations sit at the intersection of statistics and computer science, relying on concepts from probability theory, graph algorithms, machine learning, and more. They are the basis for the state-of-the-art methods in a wide variety of applications, such as medical diagnosis, image understanding, speech recognition, natural language processing, and many, many more. They are also a foundational tool in formulating many machine learning problems. This course is the second in a sequence of three. Following the first course, which focused on representation, this course addresses the question of probabilistic inference: how a PGM can be used to answer questions. Even though a PGM generally describes a very high dimensional distribution, its structure is designed so as to allow questions to be answered efficiently. The course presents both exact and approximate algorithms for different types of inference tasks, and discusses where each could best be applied. The (highly recommended) honors track contains two hands-on programming assignments, in which key routines of the most commonly used exact and approximate algorithms are implemented and applied to a real-world problem.

Time: 23h

Instructor Details

Daphne Koller

4.2 Rating
57 Reviews

Professor Daphne Koller joined the faculty at Stanford University in 1995, where she is now the Rajeev Motwani Professor in the School of Engineering. Her main research interest is in developing and using machine learning and probabilistic methods to model and analyze complex domains. Her current research projects span computational biology, computational medicine, and semantic understanding of the physical world from sensor data. She is the author of over 200 refereed publications, which have appeared in venues that range from Science to numerous conferences and journals in AI and Computer Science. She has given keynote talks at over 10 different major conferences, also spanning a variety of areas. She was awarded the Arthur Samuel Thesis Award in 1994, the Sloan Foundation Faculty Fellowship in 1996, the ONR Young Investigator Award in 1998, the Presidential Early Career Award for Scientists and Engineers (PECASE) in 1999, the IJCAI Computers and Thought Award in 2001, the Cox Medal for excellence in fostering undergraduate research at Stanford in 2003, the MacArthur Foundation Fellowship in 2004, the ACM/Infosys award in 2008, and was elected a member of the National Academy of Engineering in 2011. Daphne Koller is the founder and leader of CURIS, Stanford's summer research experience for undergraduates in computer science - a program that has trained more than 500 students in its decade of existence. In 2010, she initiated and piloted, in her Stanford class, the online ed

Probabilistic Graphical Models 1: Representation
4.5 (233 Reviews)

- Provider: Coursera
- Time: 30h

Free

Probabilistic Graphical Models 3: Learning
4.3 (33 Reviews)

- Provider: Coursera
- Time: 23h

Free

All courses by Daphne Koller

More artificial intelligence courses

Convolutional Neural Networks
5.0 (709 Reviews)

- Provider: Coursera
- Time: 21h

Free

AI For Everyone
5.0 (541 Reviews)

- Provider: Coursera
- Time: 9h

Free

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
5.0 (526 Reviews)

- Provider: Coursera
- Time: 15h

Free

A Crash Course in Data Science
5.0 (490 Reviews)

- Provider: Coursera
- Time: 5h

Free

Sequence Models
4.9 (755 Reviews)

- Provider: Coursera
- Time: 18h

Free

Open Source tools for Data Science
4.9 (485 Reviews)

- Provider: Coursera
- Time: 7h

Free

All artificial intelligence courses

Reviews

4.2

57 total reviews

5 star 4 star 3 star 2 star 1 star

Write a Review

By Marshall W on 31-Jul-17

Thumbs up for the course content. However, there are technical problems which no one is attending to. I could not submit my programming assignment, and after consulting every available resource, I was not dignified with an answer. It is a shame how such wonderful learning opportunity can become spoiled by some insignificant technical detail.By my opinion, the course should not be divided into 3 courses. Many technicalities were done sloppy in the process.

By Subhi M A on 20-Nov-16

Can't get score for free!!!

By varun b on 29-May-17

I learned pretty much from this course. It answered my quandaries from the representation course, and as well deepened my understanding of PGM.

By Karen C on 5-Nov-17

This course induces lateral thinking and deep reasoning.

By Carl E S I on 18-Mar-18

Really a interesting, challenging and great course!

By Vinayak on 6-Feb-18

Interest but difficult.

By Mahmoud S on 22-Feb-19

The honorary assignments contain code mistakes, and difficult to do! You are sifting through mistakes in the instructions along with the supplemented code!

By Deleted A on 18-Nov-18

This course seems to have been abandoned by Coursera. Mentors never reply to discussion forum posts (if there is any active mentor at all). Many assignments and tests are confusing and misleading. There are numerous materials you can find online to learn about Graphical Models than spending time & money on this.

By Jiaxing L on 27-Nov-16

I am kind of disappointed that you have to pay for the course before you can submit the solution to the problem set. However, that is not the main issue of this course, as I fully understand that the financial profit for the lecturer is very important. The main issue of this course is that the chaos in the symbol used in the second programming assignment, the lecturer cannot even main self-consistency in the symbol used. The statement of everything in both PA1 and PA2 is also very confusing.

By Hunter J on 2-May-17

The lectures are fine and the book is great, but the assignments have a lot of technical problems. I spent most of my effort trying to solve trivial issues with the sample code and dealing with the auto grader.

By Jesus I G R on 16-Oct-19

The last programming assignment is not very well designed. Also, I think that it would be better if more time was spent designing networks instead of learning the theory.

By Phillip W on 1-May-19

I enjoyed learning about this exciting field. Though, the explanations need some more examples to generalize. Also, I found that there is a big gap between the videos and the programming assignments. Either the programming assignments get more theoretical explanations, maybe with some examples too, or the videos get more applied than they are now.