Chevron Left
Retour à Bayesian Methods for Machine Learning

Avis et commentaires pour d'étudiants pour Bayesian Methods for Machine Learning par Université nationale de recherche, École des hautes études en sciences économiques

4.6
étoiles
530 évaluations
155 avis

À propos du cours

People apply Bayesian methods in many areas: from game development to drug discovery. They give superpowers to many machine learning algorithms: handling missing data, extracting much more information from small datasets. Bayesian methods also allow us to estimate uncertainty in predictions, which is a desirable feature for fields like medicine. When applied to deep learning, Bayesian methods allow you to compress your models a hundred folds, and automatically tune hyperparameters, saving your time and money. In six weeks we will discuss the basics of Bayesian methods: from how to define a probabilistic model to how to make predictions from it. We will see how one can automate this workflow and how to speed it up using some advanced techniques. We will also see applications of Bayesian methods to deep learning and how to generate new images with it. We will see how new drugs that cure severe diseases be found with Bayesian methods. Do you have technical problems? Write to us: coursera@hse.ru...

Meilleurs avis

JG

Nov 18, 2017

This course is little difficult. But I could find very helpful.\n\nAlso, I didn't find better course on Bayesian anywhere on the net. So I will recommend this if anyone wants to die into bayesian.

LB

Jun 07, 2019

Excellent course! The perfect balance of clear and relevant material and challenging but reasonable exercises. My only critique would be that one of the lecturers sounds very sleepy.

Filtrer par :

101 - 125 sur 149 Avis pour Bayesian Methods for Machine Learning

par vania j t

May 21, 2020

excellent course!

par M A B

Jul 31, 2019

Amazing contents

par Harshit S

May 15, 2019

Awesome course !

par Navruzbek

Aug 17, 2018

Great course!!!!

par Amulya R B

Nov 05, 2017

Tough but a must

par Xiaoying W

May 07, 2020

Thanks a lot!

par Jue W

Apr 30, 2019

Very helpful!

par RITICK G

Dec 22, 2019

gfhgngfbfv

par Goh

Jul 04, 2019

Excellent!

par Sankarshan M

Jul 09, 2019

very good

par Amrith S

May 17, 2018

Succinct!

par Kelvin L

May 25, 2018

Cool!!

par Dipanjan D

Jan 21, 2020

.

par Marcin L

Nov 14, 2019

The course was great, I've learned a lot about Bayesian perspective on Machine Learning. The level was satisfying, tasks and quizzes were demanding. It has been very interesting material to learn about.

I would give 5 stars, but eventually gave 4 because it had two drawbacks. First is, assignments are written in tensorflow v1, and occasionally there were issues with compatibility in some libraries. I don't know when the codes were last time refreshed, but unfortunately open source technologies tend to become deprecated very quickly, and the time has already affected course materials. Secondly, some of the most important derivations were made on blackboard, and are not included in downloadable slides. I would really like to keep them in some files, but the're not available.

Apart from these minor drawbacks, it's still a great course and definitely worth learning from.

par Mehrdad S

Sep 03, 2019

This is a great course for some of the advance topics in Baysian ML. The course starts off great and provides great explanation of the basic topics such as Conjugate, EM algorithm, etc. The related HW are also intelligently designed and fun to solve. But, as it reaches the weeks 5 and 6, things starts to fall apart and the materials are not presented and explained in the best possible way. I think the instructors try to teach many topics which requires a little bit of patience in a short amount of time. Overall, I believe its a course worthy of try, certainly provides great exposure to some of the advance topics but requires further follow ups and studies to completely digest all the materials.

par Raffael S

May 15, 2020

This course is very good. However, the weeks on Variational Methods and Gaussian Processes need more detail or references to extra reading material as they don't very much into depth. Also, a few theoretical exercises would have been nice. E.g. calculating a simple example with non-conjugate priors. Finally, I feel like the notebooks could do with a major update to TF 2.0 and Keras as well as GPy. I spend a few hours chasing non-existent bugs in my code when the problem was that the solutions changed numerically from one version to the other and you have to find out which one.

par Bart-Jan V

Nov 23, 2018

Great course, great material, though difficult to follow a non native English speaker being non-english myself. Though the instructors know what they are talking about, they don't tell it in their own words but rather seem to have practiced their text.

Another important point is that it took me a lot of time to follow (pre)calculus and probability theory courses, to be able to understand this course. The course was a nice motivation to do that. I'm glad I did, because now I can understand and use VAE's and bayesian optimization (and some other useful stuff)

par Joris D

Jul 17, 2018

I can not recommend this course highly enough. Unfortunately I can't give it 5 stars since some of the computer assignments were outdated with respect to the tools they utilize (e.g. arguments in the assignments not existing anymore). Still, let that not discourage you. If you ever mentally disconnect when people start talking about Gibbs sampling, mean field approximations, intractable variational lower bounds, or other big fancy words, this is definitely the course for you. You'll discover that all these things are actually quite straightforward.

par Saptashwa B

Mar 04, 2020

Fantastic course! Very comprehensive introduction to Bayesian analysis. There's though room for improvement from what I have experienced. One suggestion I have is to provide transcript written and checked by the lecturers and not some auto generated script! This would help us a lot better to understand the video and won't mislead us, which at times the transcript really does!!

par Maury S

Aug 22, 2018

Excellent, detailed content for people wanting to understand variational methods for machine learning. Fairly high degree of math and statistics required as a prerequisite, as well as moderate ability as a Python programmer. Does not get 5 stars because some of the assignments had confusing instructions, and availability of instructors and others to asnwer questions was poor.

par Mauro D S

Jul 03, 2018

Hard material, but very well explained. The peer-review exercises are interesting as well, but if the reviewer does not understand the material, I wonder how useful they are. Open research question I guess (i.e. how to make sure the student reviewer understands what he is reviewing-are there any baseline reviews established a student should go through first?)!

par Milos V

Jan 08, 2019

As PhD in physics I found lecture super-boring (too much theory and derivation) and irrelevant to the practical assignment. On the other hand, most of practical assignments are explained very pedagogical manner (except week 5!). As for the first course - I would recommend more code-related lectures.

par Alexander E

Jun 02, 2018

Excellent material! I got new very useful knowledge. I really like the final project. Although course design is not perfect. It would be great to have additional content (links or documents), lectures are not enough to pass the tests. Also some assigments have issues (code and grader errors).

par 魏力

Jul 21, 2018

Good course. But some suggestions: topic about variational inference or variational EM in theory is quite tough, better to have equivalent level of assignment for better practical understanding. Personally, I feel VAE is a very simplified application case.

par Gavin L

May 12, 2020

Probably the best online course available on this topic and some projects are indeed interesting and worth the investment. However, i don't feel like quizzes and some projects are challenging (or at least worth some effort) to build a solid understanding.