Machine Learning is a growing field that is used when searching the web, placing ads, credit scoring, stock trading and for many other applications.

This data science course is an introduction to machine learning and algorithms. You will develop a basic understanding of the principles of machine learning and derive practical solutions using predictive analytics. We will also examine why algorithms play an essential role in Big Data analysis.

Taught by

Ansaf Salleb-Aouissi, Cliff Stein, David Blei, Itsik Peer, Mihalis Yannakakis and Peter Orbanz

DO NOT PAY FOR THIS COURSE!!! YOU WILL GET RIPPED OFF!!!

1) The series is basically an informal presentation of topics in statistics and machine learning. THEY DON'T ACTUALLY TEACH, but rather send you a links of a whole lot of articles and papers.

2) The questions are badly worded and sometimes incorrect, where the staff has to create extra credit for their mistakes.

3) Most of the presentations are really really uninspiring. They just don't have great communication skills. No slides are available so if you want to answer a question you have to go …

DO NOT PAY FOR THIS COURSE!!! YOU WILL GET RIPPED OFF!!!

1) The series is basically an informal presentation of topics in statistics and machine learning. THEY DON'T ACTUALLY TEACH, but rather send you a links of a whole lot of articles and papers.

2) The questions are badly worded and sometimes incorrect, where the staff has to create extra credit for their mistakes.

3) Most of the presentations are really really uninspiring. They just don't have great communication skills. No slides are available so if you want to answer a question you have to go back through the video and mine for the answer which is time consuming.

If you want some other MOOCs on machine learning I suggest the following (in the following order)!

1) Coursera - Machine Learning - University of Washington

AMAZING!

2) Coursera - Machine Learning - Stanford

The course that started it all for me.

3) Stanford Lagunita - Statistical Learning.

Another classic. The free book is amazing.

3) EDX - The Analytics Edge - MIT

They really teach you the ins and outs of R programming language as well.

4) EDX - Introduction to Big Data with Apache Spark - Berkeley

It's a little advanced, but the assignments are really challenging

5) EDX - Scalable Machine Learning - Berkeley

It's a little advanced, but the assignments are really challenging

So the summary of this review is:

DON'T TAKE DS102X: Machine Learning for Data Science and Analytics!

DON'T TAKE DS102X: Machine Learning for Data Science and Analytics!

DON'T TAKE DS102X: Machine Learning for Data Science and Analytics!

DON'T TAKE DS102X: Machine Learning for Data Science and Analytics!

DON'T TAKE DS102X: Machine Learning for Data Science and Analytics!

DON'T TAKE DS102X: Machine Learning for Data Science and Analytics!

DON'T TAKE DS102X: Machine Learning for Data Science and Analytics!

DON'T TAKE DS102X: Machine Learning for Data Science and Analytics!

It is about algorithms, which is nice, they'll familiarise you (by their lectures) with all the most common types of algorithms.

Now, the next question is, do you get to implement the algorithms? THE ANSWER IS NO. You don't have any programming assignments to do. All they give you are pseudo codes.

Now you may ask, what does algorithms have to do with Machine Learning? Well, the link , as presented by this course, is not really clear. Honestly, if you rename this course into 'Introduction to THEORETICAL algorithm'…

This course is not about Machine Learning

It is about algorithms, which is nice, they'll familiarise you (by their lectures) with all the most common types of algorithms.

Now, the next question is, do you get to implement the algorithms? THE ANSWER IS NO. You don't have any programming assignments to do. All they give you are pseudo codes.

Now you may ask, what does algorithms have to do with Machine Learning? Well, the link , as presented by this course, is not really clear. Honestly, if you rename this course into 'Introduction to THEORETICAL algorithm', the course meaning will actually be more appropriate.

Now, there's no programming assignments, what are you gonna do for the quizzes? Okay, the answer is: mostly yes, no questions, some trivial sorting questions which you can do with a pencil. That's it, you don't need more than high school math to do them.

Honestly, I don't understand why the course name is Machine Learning while most of the content is about algorithm, and worse, there's no practice for the algorithms also.

Don't pay 99USD, enough said. You'll better off investing in MITx 6.002x, which teach algorithms too, but provide much richer learning experience, for 50USD only.

I mostly enjoyed the experience as I found the course interesting. The content is so rich. Of course you can expect some differences from a speaker to another one given the large number of speakers and the many covered topics, however, despite this, this course has worked for me. It helped me understand ML little by little resolving lots of confusions about how ml and stats work together which were not removed in may other courses that I took online. It gives the basic ideas of important concepts of data science, algorithms and machine learning that I didn’t find elsewhere. It is of course not realistic to assume that it will make you a data scientist over night but it is a good platform to start with.

Allisonpartially completed this course, spending 5 hours a week on it and found the course difficulty to be medium.

The lectures are nice and the material is very interesting, but they assume you are already familiar with the material. There are not very many questions, and they're either very simplistic and not really useful or overly hard (especially if you have had no exposure to the material). It would be nice to have better exercises that help students to understand the lecture material. In this run of the course there were a number of errors in the wording of the questions. The discussion board is hardly monitored by staff, and questions and concerns are not dealt with. It is hard to understand who this course will help.

The course sure covers a wide range of topics but the the content is interesting and intriguing. It does help in learning lots of tools to be able to explore further. Although the proportion of algorithms is bit bigger than expected but the course does provide a good overview of the field. A nice learning experience overall. Can help to better understand the other machine learning and data science courses.

There's no clear objective for this course and its syllabus ran like an extended introduction to everything and anything we can think off. The treatment of subjects being covered range from elementary (linear programming) or to downright abysmal for NP-completeness.

Unless you have plenty of time and money to burn - no recommended at all.

Many Machine Learning courses neglect explaining the various more basic and general algorithms used when creating ML ones. A very well explained class, especially chapters 4 and 5.

by
Dissipatedropped this course, spending 4 hours a week on it and found the course difficulty to be medium.

Like an earlier reviewer said, it is unclear who this course is meant to be for, and the outcome they aim to help learners achieve.

Week 1 consists general information and background on, and the future of, data science. Weeks 2 and 3 breeze through statistics, so you really have to have your elementary statistics down pat to be able to keep up. In addition, most of the lectures for Weeks 2 and 3 were given by a lecturer in respect of which English is not her first language, and I had some trouble following her.

Week 4 covers exploratory data analysis and visualizatio…

Like an earlier reviewer said, it is unclear who this course is meant to be for, and the outcome they aim to help learners achieve.

Week 1 consists general information and background on, and the future of, data science. Weeks 2 and 3 breeze through statistics, so you really have to have your elementary statistics down pat to be able to keep up. In addition, most of the lectures for Weeks 2 and 3 were given by a lecturer in respect of which English is not her first language, and I had some trouble following her.

Week 4 covers exploratory data analysis and visualization. Week 5 is on Bayesian Modelling.

Given that Weeks 2 and 3 covered statistics only briefly, I decided to drop out mid-Week 2 to find something more comprehensive on the topics in Week 4 and 5.

The quizzes were not really helpful in that although they would give the correct answer, it did not come with any explanation as to why that was the correct answer and the rest of the answers were wrong.

In general, topics in this course were covered briefly and broadly, and I see this course as more of a general overview of the area of data science , but not for beginners in statistics.