Chevron Left
Machine Learning: Clustering & Retrieval(으)로 돌아가기

워싱턴 대학교의 Machine Learning: Clustering & Retrieval 학습자 리뷰 및 피드백

4.6
1,828개의 평가
314개의 리뷰

강좌 소개

Case Studies: Finding Similar Documents A reader is interested in a specific news article and you want to find similar articles to recommend. What is the right notion of similarity? Moreover, what if there are millions of other documents? Each time you want to a retrieve a new document, do you need to search through all other documents? How do you group similar documents together? How do you discover new, emerging topics that the documents cover? In this third case study, finding similar documents, you will examine similarity-based algorithms for retrieval. In this course, you will also examine structured representations for describing the documents in the corpus, including clustering and mixed membership models, such as latent Dirichlet allocation (LDA). You will implement expectation maximization (EM) to learn the document clusterings, and see how to scale the methods using MapReduce. Learning Outcomes: By the end of this course, you will be able to: -Create a document retrieval system using k-nearest neighbors. -Identify various similarity metrics for text data. -Reduce computations in k-nearest neighbor search by using KD-trees. -Produce approximate nearest neighbors using locality sensitive hashing. -Compare and contrast supervised and unsupervised learning tasks. -Cluster documents by topic using k-means. -Describe how to parallelize k-means using MapReduce. -Examine probabilistic clustering approaches using mixtures models. -Fit a mixture of Gaussian model using expectation maximization (EM). -Perform mixed membership modeling using latent Dirichlet allocation (LDA). -Describe the steps of a Gibbs sampler and how to use its output to draw inferences. -Compare and contrast initialization techniques for non-convex optimization objectives. -Implement these techniques in Python....

최상위 리뷰

JM

Jan 17, 2017

Excellent course, well thought out lectures and problem sets. The programming assignments offer an appropriate amount of guidance that allows the students to work through the material on their own.

BK

Aug 25, 2016

excellent material! It would be nice, however, to mention some reading material, books or articles, for those interested in the details and the theories behind the concepts presented in the course.

필터링 기준:

Machine Learning: Clustering & Retrieval의 302개 리뷰 중 1~25

교육 기관: Ernie M

Sep 25, 2017

I enrolled in this specialization to learn machine learning using GraphLab Create. Half way into the specialization the creators sold Turi, GrapLab's parent company, making it non available to the general public (not even by paying) and then all the knowledge devalued. I wish I had known this and I would have enrolled on a different specialization. The creators still give you the possibility of using numpy, scikit learn and pandas but I had already done a lot with GraphLab create. The time I invested on my nights after work became a waste. I was trying to convince the company I worked for to buy licenses for GraphLab create.

Coursera should not allow folks to create courses that promote a private license course because it would make people waste their time and money if they decide to privatize the software.

Don't take this course, and if you take it then only use GraphLab create when the authors give you no other option.

Teaching style: Carlos was good, Emily is not very clear and loses focus of the topics and often rambles. She seems very knowledgeable but she lacks clarity of exposition when compared to Carlos or Andrew Ng.

교육 기관: Eugene K

Feb 10, 2017

If you are considering this specialization I would recommend the Andrew Ng course instead and the main reason is that it isn't depend on proprietary ML framework. Despite the good lectures, the assignments don't help you develop the knowledge required for ML developer role.

Taking in consideration the permanent postponing the courses delivery, from summer 2016 to summer 2017, finally the most interesting part of the specialization was cancelled. I'm completely disappointed with the specialization learning expirience.

교육 기관: akashkr1498

Jul 08, 2019

I like the course very much. I learnt so many advance concept and real life implementation.. but slightly disappointed by the quiz question please be specific what you wanted us to answer. looking forward for SVM and deep learning material.

교육 기관: Tsz W K

May 15, 2017

The materials presented are excellent with well prepared skeleton codes for all ML models. Comparing this course to its three preceding ones, this course is more challenging both conceptually and computationally. The slight drawback is that, because of the highly technical nature of the last three weeks' materials, there isn't enough guidance about how one may construct the ML algorithms from scratch, that is, learners with less experience in computing will, more or less, have to accept the sample codes with little confidence about how to (re)write such codes in the first place.

As a result, I believe that learners with more experience in algorithms and data structure (or learners who proceed to learn more about this area) are likely to gain more from this course for at least two reasons: i) they are more comfortable with the complicated ML algorithms; ii) they can improve the algorithms to speed up the estimation time (some advanced techniques are quite computationally expensive, say over 20 minutes).

In general, I have learnt very much from this course and love it.

교육 기관: André F d A F C

Jul 25, 2016

I found this Course less well prepared than the previous 3 modules. Misleading hints in the assignments, code errors, etc... Also, I found the amount of work required higher, which is not in itself a bad thing, just a bit unexpected.

교육 기관: Hamel H

Aug 07, 2016

This course rushed through the material at the end.

교육 기관: James F

Aug 10, 2016

The course, and indeed the whole specialization, was advertised as not requiring the Graphlab Create toolkit. This is untrue, as the final programming assignment does require it. The general dependence on SFrame is understandable since it is open source, but requiring any interaction with a licensed product (even if temporary and research licenses are available) greatly negatively impacted my experience in this course.

교육 기관: Phil B

Feb 13, 2018

Again the lecturing style and course content were excellent, allowing us to write fairly complex functions to implement our own algorithms from scratch but also using pre-built functions when necessary to allow us to explore the effects of different variables. The benefits and costs of the different types of clustering were clearly stated. It's a shame that the specialization stops here, as a capstone project with the same quality of these 4 courses would really provide the students with something they can show off to potential employers. The problem most students will have when coming off this specialization is how to implement and deploy your own model into a service like a website.

교육 기관: Edward F

Jun 25, 2017

I took the 4 (formerly 6) courses that comprised this certification, so I'm going to provide the same review for all of them.

This course and the specialization are fantastic. The subject matter is very interesting, at least to me, and the professors are excellent, conveying what could be considered advanced material in a very down-to-Earth way. The tools they provide to examine the material are useful and they stretch you out just far enough.

My only regret/negative is that they were unable to complete the full syllabus promised for this specialization, which included recommender systems and deep learning. I hope they get to do that some day.

교육 기관: Sean S

Apr 03, 2018

Another great course and sadly the last of this specialization. I found the material for this course to be the most challenging yet, specifically the LDA module. The programming assignments were all very manageable thanks to graphlab and the very explicit hints provided but I do not feel like I reached the same level of understanding as I did for the previous courses in the specialization. I have grown to enjoy using graphlab and would likely use it going forward if not for the licensing. I am very disappointed that the remaining courses will not be offered and am now in search for another great machine learning resource.

교육 기관: leonardo d

Aug 25, 2019

Awesome course. It was great to learn modern tools in machine learning, not just to apply some black-box on data. I also loved the applications that were showed: it is fantastic to see the algorithms in action, knowing how everything works inside. Another exiting ingredient was how the teachers show you the advantages and weaknesses of each method, as well as the suitable places were they can be applied, or even the most popular extensions or alternatives. I was really really great to had spent those months understanding machine learning in this course and during this favoluos entire specialization.

교육 기관: Luiz C

Jul 10, 2018

An excellent Course. I was first doubtful about my interest for this Course, having already read mover Clustering. But this Course surprised me: it more than delivered, presented advanced concepts used in real world, always in a clear and engaging approach. The Tutor of this Course is a key component of my appreciation of this Course. To sum up, great content, great materials (Excellement videos, excellent slides, great assignemtns and quizzes - not a single bug!!!) in a very pleasant and engaging presentation. One work... THANK YOU

교육 기관: vacous

Apr 18, 2018

Very good content, and great practices. Coding a algorithm from the scratch definitely helped my understanding. The more challenging knowledge like LDA and HMM in the last two weeks are not covered well in great details, but I can understand the course design since that the foundation knowledge required to understand of those algorithms are much more advanced than the previous ones.

Overall, I enjoy this course and the specilization overall, except the Graphlab part which is very confusing and rarely used in the industry.

교육 기관: Kim K L

Oct 04, 2016

Another super course. Though admittedly (for me at least) very difficult to make within the allotted time given for one period of the Course. Lots of advanced stuff that require substantial studies to really comprehend, i.e., it should never be enough just to hack & run the code (that's the easier challenge). Still have a long washing list of topics coming out of this Course that I need (want) to understand better. But at least the background to do so is neatly provided here. So without further ado ... Applause!

교육 기관: Uday A

Aug 13, 2017

Thank you so much, Emily and Carlos! Really liked all the courses, and I daresay these are the best ML courses available online. Very insightful, and also cover the mathematical part of the algorithms. Since there are now just 4 courses in this ML Specialization, I would mostly jump to Andrew Ng's new Deep Learning Specialization for further studies. But will look out for your remaining courses to be available once more. If and when they come out, it would be great to send out a notification. Thanks!

교육 기관: Ridhwanul H

Oct 17, 2017

Like all the other ones, this as well was an amazing course. The topics covered in were the most interesting ones till now for me, as earlier days when I started programming I used often think about problems like these and used to wonder how it was done. Now I feel like I might be able to do them.

Its a shame that you no longer provide the Recommender System course, since that was something I was even more interested in, and its kinda sad that I am not gonna have access to it.

교육 기관: Abhilash V

Feb 20, 2017

A great course as the other 3 courses in the specialization.This course introduces and make us implement Knn,Kd trees,Gaussian Mixture model and LDA model for clustering and retrieval.The data set is the peoples wiki from the Foundations course and theres a assignment on clustering images too.If you have taken the other 3 an do this with ease and if you haven't taken those i think it will be better to take this course after the other 3.

교육 기관: Swati D

May 02, 2018

This course is a very structured and progressive learning. It is an advantage , if we know python . However, one can still manage and explore Machine learning and Deep learning concept of AI. The case study and real life approach keeps your quest on. This is a great initiative and gives us an opportunity to be future ready while at job. Many notion went wrong about AI and the chapters are well designed to keep us engaged while we

교육 기관: Jie S

Dec 27, 2019

Overall, this course covers a lot of materials on clustering methods and algorithms. The assignment instructions are well-prepared. One thing I was struggling with is that I had to install Turicreate on a Linux system, which was a painful experience. It is recommended that the course team advise on how to install Turicreate less painfully on a Windows machine. Other than this, I think it was a great course!

교육 기관: Ferenc F P

Jan 25, 2018

Very good course. Even though I had some machine learning background, this course provided new insights and new algorithms, like KDTree, Locally Sensitive Hashing, Latent Dirichlet Allocation, and mixture of Gaussians. the only drawback is that with scikitlearn, not always you get the same results as with GraphLab. Thanks for the instructors for this great specialization.

교육 기관: Stephen G

Aug 14, 2016

Yet another really excellent course in this series - the best online course I have ever taken. I really appreciate the fairly high level on which it is taught, and the speed with which they go through the material - it is not here to entertain or waste time, but to get straight to the point - what can I do, and how do I use open source tools to do it?

교육 기관: Feng G

Aug 09, 2018

Emily is an extremely awesome instructor. For those who have some background in statistics, biostats , econometrics and math and want to study machine learning by themselves, these modules can be an outline that introduce basic topics in machine learning.

I'm looking forward to see more advanced courses in these topics from Carlos and Emily.

교육 기관: Miguel P

Jul 13, 2016

I loved the previous 3 courses and what I saw in this course so far seems pretty interesting. I'm really sad that Coursera decided to block access to assignments for not paying users. I really wanted to continue with the specialization but I already purchased another specialization, so I'm going to have to put this course on hold for a now.

교육 기관: Alessio D M

Aug 01, 2016

Very nice course, and a great grasp on clustering techniques. If I could just suggest something to improve, it would be the section on LDA and Gibbs: it's very high level and it would be really nice to have some more technical insights on those techniques (perhaps with optional sections, as for other topics).

교육 기관: Muhammad W K

Oct 22, 2019

A great course to get the grass-root level understanding of Clustering and Retrieval tasks and going beyond to Unsupervised learning and the core concepts related to it. And starting from the basics all the way to some of the advanced algorithms and models used in the world today. It is simply awesome!