Chevron Left
Back to Machine Learning Foundations: A Case Study Approach

Learner Reviews & Feedback for Machine Learning Foundations: A Case Study Approach by University of Washington

13,226 ratings

About the Course

Do you have data and wonder what it can tell you? Do you need a deeper understanding of the core ways in which machine learning can improve your business? Do you want to be able to converse with specialists about anything from regression and classification to deep learning and recommender systems? In this course, you will get hands-on experience with machine learning from a series of practical case-studies. At the end of the first course you will have studied how to predict house prices based on house-level features, analyze sentiment from user reviews, retrieve documents of interest, recommend products, and search for images. Through hands-on practice with these use cases, you will be able to apply machine learning methods in a wide range of domains. This first course treats the machine learning method as a black box. Using this abstraction, you will focus on understanding tasks of interest, matching these tasks to machine learning tools, and assessing the quality of the output. In subsequent courses, you will delve into the components of this black box by examining models and algorithms. Together, these pieces form the machine learning pipeline, which you will use in developing intelligent applications. Learning Outcomes: By the end of this course, you will be able to: -Identify potential applications of machine learning in practice. -Describe the core differences in analyses enabled by regression, classification, and clustering. -Select the appropriate machine learning task for a potential application. -Apply regression, classification, clustering, retrieval, recommender systems, and deep learning. -Represent your data as features to serve as input to machine learning models. -Assess the model quality in terms of relevant error metrics for each task. -Utilize a dataset to fit a model to analyze new data. -Build an end-to-end application that uses machine learning at its core. -Implement these techniques in Python....

Top reviews


Aug 18, 2019

The course was well designed and delivered by all the trainers with the help of case study and great examples.

The forums and discussions were really useful and helpful while doing the assignments.


Oct 16, 2016

Very good overview of ML. The GraphLab api wasn't that bad, and also it was very wise of the instructors to allow the use of other ML packages. Overall i enjoyed it very much and also leaned very much

Filter by:

51 - 75 of 3,070 Reviews for Machine Learning Foundations: A Case Study Approach

By Dmitry V

Apr 1, 2016

I'm sorry, but this is just ridiculous. I can't recommend this course to anyone. It's all about advertizing: Emily Fox can't stop but recommend Amazon services, and Carlos Guestrin does the same for his Dato's Graphlab Create, which is might be great in general, but absolutely useless in educational purposes. The practice part of every week is just a waste of the time.

I can't say "money well spent".

By 郑轶松

Dec 27, 2015

LIKE an advertisment!

Why not use pandas and numpy sk-learn?

Open source is more popular!

By Arun J

Sep 18, 2018

not useful since the material covered lacks any rigor.

By Mike L

Sep 6, 2016

Might be good for someone looking for a casual overview?

I really wanted to like this course, and was excited about the series. Very disappointing. Refunded after scoring 100% on first three weeks and watching the theory portion of week 4. I was familiar, with the subject prior to taking this course; was hoping for a deep dive.

Too many trivially short and low information density videos. Handwavy mathematics. I would have liked to get a more solid idea of the depth of the series from the first course before committing money.

Default software for the course has near-zero market penetration (per, unless maybe you work at Apple -- not really excusable for something that purports real-world value. Yes, you can use other software, *except for the capstone*, per another reviewer: this is fatal.

Presenters just not fully prepared to lecture on the topic: the nail in the coffin was the end of the week 4 lectures on clustering: "So, at this point, you really should be able to go out there and build a really cool retrieval system for doing news article retrieval. Or any other really, really, really cool retrieval that I can't think of right now. But of course there's lots of interesting examples. So go out there and think of ideas that I can't think of right now." Really? How about: "Cut! Take two."

Many poor design choices for the presentation. Too much time spent writing things on slides that should have already been on the slides.

As of this review: no reviews on the last courses in the series, and some poor (but indicative) reviews of the other courses.

By Jakub A

Mar 16, 2020

Definitely too little detail, too little math - for people with academic background this course may be confusing and, ironically, hard to understand because it tries to be "intuitive" - omitting the important details and formalities, in other words. The biggest downside is the TuriCreate library - it's not well known, uses other syntax than popular libraries like Pandas or Scikit-learn for some strange reason, and does not have impact when written on CV. I've known about 3/4 of the course beforehand and it was both not good for recalling the prior knowledge and for learning new things (I don't feel I understand anything new from this course). A big letdown overall.

By Hamid N

Dec 26, 2020

I found it very annoying and unprofessional to use a different library (graphlab) in the videos and instructions than what has been asked us to use (turicreate). Making jokes and trying to seem friendly is not what (at least the only thing) that makes a course a great course. Please re-record the videos or at least add instructions as for how codes in the old library are translated in the new library. I was looking forward to finish this course but I have to cancel since I don't want to waste my time googling for each single function to find its equivalent in the new library.

By Sujith S M

Jun 7, 2020

The course content is really nice however it is nearly impossible to install the turiconnect to my machine as it wont support Python Version 3.8 and i saw many people complain about the same.

I tried with Anaconda,Ubundu WSL and then i learn i need to be a programming expert to install this software and i do not think it is worth to put my whole effort just to install a software.

Atleast i would expect the instructors to give a detailed description how to install the necessary tools then it will be helpful.Hence i wont recommend this course to anyone


May 31, 2020

Faced too many issues during oncourse period.

Still feel the teaching is outdated from software point of view

Issues was started the moment the .zip files had to be extracted and to be fed in Jupiter notebook.

My suggestion to coursera: Kindly change the description of the course for Intermediate who have previous knowledge on coding, but not for Beginners.... We struggled alot.

By Winston H

Feb 24, 2020

This is the most junk and worst course I have ever taken. It has been so many years, and the software recommended by the two doctors cannot be installed at all. Now the most popular numpy and pandas are not mentioned at all in the course. All the videos are related to the junk-like software. I don't know why such quality courses can still be put on the coursera platform.

By Toma K

Jun 11, 2019

Warning! I paid for the specialization and now it tells me that the course ended 2 months ago!! i can't complete quizes which is why i paid!!! no options available to contact support.... no refund available....

By Pablo S

Jul 22, 2019

I should have read the negative reviews before wasting two full days trying, and failing, to install the required software. I urge anyone reading this to avoid this course and look for alternatives.

By Xing W

Jul 3, 2016

I was expecting to solve problems using more open-sourced package. Unfortunately, I feel this series of courses are more of an advertisement for the instructor's software company.

By Eduardo R R

Sep 23, 2015

This course rely on commercial library. I am sorry, I don't believe the convenience of a commercial library is good for your learning. You may end up locked in.

By Dmitri K

May 26, 2016

The whole course based on some proprietary software. In general, it seems that the main goal of the course is promote that software.

By sravan

Oct 13, 2016

there is no proper documentation.

at least there should be some clear instructions for first program

By Mario L

Nov 24, 2015

I dont like the tools they used, it seems like a promotion for their company.

By Lester L

Mar 21, 2020

Not made for Windows, you need a linux or mac VM to apply this course.

By Tim B

Jun 4, 2019

Complete waste of time until it is written using open-source packages.

By Phillip B

Sep 25, 2015

Would have greatly preferred if open source tools were used.

By Chandrakant M

Sep 6, 2016

I felt that I paid for demo of the Dato/Turi.

By Nitin K

Sep 12, 2019

Not good support to learning process.

By Nik M N N G

Feb 11, 2020

The material in this course severely needs an update. Some of the code examples (not from the video, because the video is obviously from old materials) are problematic. It's an interesting experience to learn a new library but I wish the experience is different. The quiz should be tougher in my honest opinion.

By Nafi A K

Oct 15, 2017

the course contains misleading information about a capstone project that I discovered -by coincidence - that is no longer exists, the video introduction and the final videos is mentioning the capstone project time and again ! , I think this is a major problem bacause such project was one of the most usefull demonstration of the skills that one could acquire from the course, if I knew this before I would not have enrolled in this course, unfortunatly I discovered this when I am already in the second Regression course!

By Brent K

Dec 15, 2022

I am so disappointed with this class. I really looked forward to a case study approach that was hands-on. But the instructors have left UWashington (they are both at Stanford now), the full curriculum was never completed, and nobody has updated the class despite the software being radically updated and rearranged after lectures were filmed. Hence, while the teaching is pretty clear, there is no way for the student to follow along on his/her own. UWashington tried to update the Jupyter Notebook pages to try to show how things work with the new software, but those updates were inadequate to enable a student to pass the quizzes. I was never able to get past quiz 3, and had to guess at some of the questions in quiz 2 because the software was not able to provide the information needed to answer quiz questions.

Further, if you are using a Windows machine, the software doesn't work, unless you run Linux in a Docker app or run it in WSL. There, of course, is absolutely NO help from the instruction material on how to do this, and only by digging in the forums can one get some ideas about how to get it working. THIS IS REALLY UNACCEPTABLE for a course from a reputable university that I'm paying for.


The course desperately needs to be filmed again and instructions updated. The lectures are great, but the video part of actually building software to do what the lectures teach is in desperate need of updating to match the current state of the software.

And in case you think that this review is coming from someone who doesn't have a clue...

I am a retired programmer, having worked on advanced simulation and AI software for R&D groups in both Lockheed Martin and IBM for 40 years. I know my way around Macs, Windows, and Linux OSs. While my python skills are not to the level of my C and C++ skills, I have been actively writing python code for the past 6 months. I.e., I know how to program (well) and am (usually) smart enough to work around obstacles and poor documentation.

By Vishok G

Oct 12, 2020

IF you are a beginner who would like to take up a job in a Data Science related field, read on:

The packages used here are not listed in a single job requirement in Angel, Glassdoor, etc. I know they said use the tools you want to, but most people taking up courses like this or similar are people with none or limited experience in Machine Learning. Rather than promoting tools created by the professor (Turi; Read the Wikipedia page, it seems like an advertisement) they need to use tools that are widely used in the industry.

(Though Turi has been acquired by Apple, the scope is very limited)

Furthermore, due to lack of proper support and solutions on sites like Stack Overflow, it gets harder for a person who lacks programming experience to debug if any problems arise

**THE BIGGEST ISSUE: Turi is NOT SUPPORTED on Windows!** I had to use a virtual environment in Ubuntu Terminal. (I may be wrong with the exact wording) For finding out how to use the package read this:

(Funny thing, the author of the page actually wrote "If you are taking the Machine Learning Foundations: A Case Study Approach", meaning someone would rarely use it for anything else IF they do)

Concept Explanation was good, but the above point was a major disappointment because I had to learn packages like Pandas and Scikit-Learn (Any job listing on Machine Learning using Python would list these as a MUST requirement. Besides, the support available on Stack Overflow is huge) after learning a package I would never use in my job.

So my suggestion is if you don't mind learning Turi and would like a surface level explanation of the concepts, go on.