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

4.6
stars
13,374 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

BL

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

PM

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.

Filter by:

3026 - 3050 of 3,115 Reviews for Machine Learning Foundations: A Case Study Approach

By Diego N

•

Dec 18, 2015

Having done some other machine learning MOOCS , this course seemed rather basic to me and did not enjoy too much using non open-source software for the programming assignments. The material is nice, In this sense, I would have expected to 'default' to sci-kit learn and offer using graphlab create as optional.

By Advait S

•

Jan 10, 2018

While it was good for learning concepts I had real trouble with graphlab. Installation of graphlab never worked on my machine. I had to install VM just for being able to use graphlab. I really wish they had opted for more open source, free options or at least used ince such library along with graphlab.

By Vincent L P

•

Feb 13, 2024

The course seems interesting on certain points and the trainers are motivated. But it is cut short at the end of its content, and the trainers present this part, which is no longer available, as the most interesting. It's too frustrating to continue a course if you know you can't really finish it.

By Ziqian G

•

Aug 11, 2020

There are big problems in this course, like the installation process should be given in a more specific and vivid way so that I would not have spent three days on it being a windows user...(update: still can't access jupyter notebook after trying installing ubuntu, vmware workstation, filezilla).

By Sunaad R

•

Jul 30, 2018

Too much dependency on Graphlab package is bad. If we are learning the concept, we should reduce the size of the sample data. We should be using generic open packages, so that our learning can be easily demonstrated anywhere (especially interviews), and not dependent on graphlab.

By kunjan k

•

Nov 5, 2015

The case study approach is a great idea.

But I wish the instructors were more candid about the tools that were in use. It seems dodgy that the instructor is a CEO of a commercial tool vendor and is "encouraging" students to use it.

The quizzes in the course were extremely shallow.

By Robert R

•

May 5, 2021

I believe these packages are out of date and the application side is not helpful.

The information on the theoretical side of things was extremely helpful to help build up my machine learning knowledge, but overall I don't feel like I'm taking away much from this course.

By Raphael R

•

Mar 19, 2016

The overall quality of the course is good, but in my opinion the level is quite low and there is less content then I expected. The assignments are more or less copy-paste or very repetitive. The 5-8 hour work per week are a joke, I never needed more than 2.5h per week.

By Matthew F

•

Jul 21, 2019

Focused too much on graphlab as opposed to the ML. If the course was titled ML with GraphLab I wouldn't mind (and wouldn't have signed up). The gaffs are kind of charming but really I would expect some of the videos to have had another take or two.

By Joseph J F

•

Aug 20, 2017

It is more a course in using the tools designed by the teachers than machine learning. It might do something for a less experienced user in programming, but I didn't find it much use. The overview of Machine Learning tasks isn't bad.

By Andras H

•

May 31, 2020

on one hand good... on other hand annoying ( mixing graphlab and turicreate... shitty wording of the assignment task, info added as side note which was vital for the assignments...etc.) The curse material would need a refresh.

By Sunil T

•

May 24, 2020

SFrame data do not support by an updated version of the Python, so student won't able to finish their assignments. So instructor need to update the materials and database which is supported by a new version of Python

By Tudor S

•

Apr 22, 2018

The Assignments and Quiz questions are hard to read and comprehend.

Although individually the course presentations are ok, overall this course isn't a very relevant or coherent introduction to Machine Learning.

By Taylor I

•

May 11, 2020

Feel like I have been duped in a way. No capstone project and you are pretty much forced to use Turi Create (proprietary/black-box version of pandas), which I found incredibly hard to install and use.

By Ashley

•

Jun 23, 2019

Content is outdated and should be revamp, the library use in this course is only for python 2.6 which is legacy and should be updated to latest python version using skicit learn instead of graphlab.

By Arman A

•

Feb 16, 2016

The course uses proprietary tools for machine learning and data manipulation, making it effectively useless! However, the material on describing the machine learning algorithms were excellent!

By Annemarie S

•

May 24, 2019

The instruction conceptually is fine, but I really disliked dealing with setting up Graph Lab Create and SFrames when we could have instead been using more commonly used open source software.

By Charan S

•

Jul 16, 2017

If someone is looking for ML foundations and what is ML, they can choose this course. This is very basic course and i feel should be excluded from the ML specialization.

By Aqui M

•

Mar 5, 2016

One would learn a thing or two, but the course is very sparse compared to other machine learning courses, and I didn't feel that it was worth the time and the cost.

By Robert M

•

Oct 27, 2015

I do not like this course being tied to a commercial product. In my opinion it should be using an open source python library and not focusing on the Dato product.

By Evlampi H

•

Nov 5, 2015

The framework is ok, but it would be more insight on the functions would be much more amplifying the learning process.

Good working examples, though!

By shanky s

•

Apr 26, 2021

I thought that indepth will be taught and enrolled for this course, but unfortunately its only basics. I wasted my enrollement

By Simone V

•

Apr 21, 2022

It started nice but there are some basic aspects, like installing Turi Create, neglected. I had to withdraw from the course.

By Piotr T

•

Oct 6, 2015

it's rather a course on using API of proprietary software with very very basic background on the actual math underneath

By A C

•

Jun 21, 2023

Needs to be updated. Graphlabs seems impossible to install. Needs an older version of PIP, non compatible with M1 Macs