this course was awesome from learning point of view as it was more detailed and required pre beginners knowledge about key concepts to move ahead . i have learned many concepts about machine learning models,

statistics , theory implementation part.

what i most enjoyed was the lab work as it was more detailed and there were plenty of things to learn from .

This course is very great. it focuses mainly on codes and how to get your models trained well with the best results. and for that a prior knowledge of the algorithms and the coding language in addition to the different libraries would be better.

Easy to understand and apply (+). Some code uses deprecated functions/methods. (-) Assignment answers seem to be mixed up (on very few occasions) so one has to randomly try out the correct answer to get 100%. (-) Issues reported.

4/5 simply because not all the lesson Jupyter Notebooks are downloadable--the download links do not work. But the course content is very educational and has a good balance of difficulty enough to challenge you while learning.

It's a nice course it deserve a 5/5 but some common and better regression algorithm like Decision Trees and Random Forest were not taught unlike the Classification part. Thanks

very clear contents and explanations. Regression methods are thoroughly explained. Examples of coding are indeed a very good basis to start coding on the project.

AN amazing course and contain really time values content only regret is that coursera doesn't come in dark mode

Interesting course focusing more on the regression for the machine learning

Very helpful course. There are few ups and downs but overall its helpful.

Good course with nice exemple for illustration

A great course to kick start your ML journey.

this course material was so helpful

An truly exciting course!

thorough and well taught

I like this is cuourse

Great course

very intense

best course

excellent

Excellent

good one

GOOD

Nice

Overall a good course. Nothing special though. In detail: Pros: 1. Very good example code (jupyter notebooks) given. Can even be studied stanalone. Can be used as a reference for future cases. 2. Provides an holistic view in the regression pipeline. Cons: 1. The course is outdated and not very professional and this is obvious in various examples, to name a few: a) There are some syntax errors in the notebooks. b) There are English grammatical/syntax errors. c) There is content in the notebooks that was never introduced in the videos (SGD). d) There are video duplicates with different naming. e) The provided notebooks (normally 2 notebooks) each week are sometimes provided is wrong chronological order. 2. The course lacks mathematical foundation. In order to fully understand the topic you need to read theory from other resources in parallel. 3. The instructor clearly reads a pre-written text and making his speech monotonic and hard to follow. 4. The slides are boring and highly simplistic.

The focus on the different views on regularization and their importance in the quiz seems overrated. While they are a good way to understand what regularization really is, it seems not too relevant for daily practical use. And since the different views all describe the same thing it's not a good way to have all those questions on them in the quiz, because essentially every answer would be true. Instead it would make sense to focus more on the different types of regularization, how they differ and their respective implementations in sklearn.