Google's Machine Learning Crash Course

This course is not meant to teach ML to anyone. It is a marketing push for Tensorflow. Stick to books and academia courses

I have a BS is computer science as well and the coding practices were rough. The videos and other explanations were fairly simple but when it said "# your code here" I struggled.

You will find each of the chapters in the course has a video lecture with full-text support. The curriculum is extremely detailed for you to understand easily. It also offers a Programming Challenge page where the code is presented in a dynamic way on the browser, where you can run it as well as modify it. The curriculum has interactive exercises for you with interactive visualizations of ML principles and questions on the current topics. This free course is perfect.

Its undoubtedly a great online course. But what I seriously think is that each person who completes the course, might take-away different learning outcomes. For some, it could be a naive repetition of the same concepts and they might feel wastage of time. So if you are a kind of person who is already into the game and have even a decent amount of experience in data modeling (including neural nets), then this course is definitely not for you. However, if you are just starting and if you have or dont have programming experience, then you will enjoy this course. Its pretty short and you have the liberty to decide your own pace.

One of the things I like most about it is, its actually put on by the people that are involved in various projects in Google. You get to learn from the data engineers and data scientists at Google around their approach to how to implement these and walk through. Like I said, not always just video. Some of it has reading. Then you have code to back it up. Its definitely something thats awesome.

For a 15 hours course (it took me far longer than that), it does pretty well on presenting the basic theory necessary to apply it in easy but still increasingly complex exercises.

As a casual learner of ML and only spending an hour or two so far on this, I can say I really like the structure/format of this course.

I've been trying to get through the tensorflow crash course provided by google but i'm having exceptional difficulty with understanding the code. It seems like the concepts are presented really generally but the code goes into hyper detail without any explanation.

Google's machine learning course is amongst the best in the world. Infact, Google was one of the first companies to start the machine learning course.

Its one of the recommended courses for Machine learning enthusiasts. But for people who are completely new to this domain needs to brush up programming language (Python, recommended) and algorithmic skills.

Googles ML crash course covers logistic regression and neural nets - probably multi-layer perceptrons with a (multiclass) logistic regression output. Seems like it is just an advertising investment by Google to get people on TensorFlow and Google Cloud Platform.