Jeremy from fast.ai here - I teach this course. Let me know if you have any questions about it (or else head over to http://forums.fast.ai for the dedicated course forum if it's a more specific technical question).
1. How exactly it is different from Andrew NG's course, other than Octave/Matlab vs Python? As someone who is new to ML and wants an introduction, I am now confused which course I should do.
2. What are the math prerequisites? Do you also cover them in the course or is there any list materials available to prep?
Sometimes I'll assume some understanding of basic linear algebra or probability distributions when explaining why something works. Particularly for the naive Bayes section.
The first half of the course assumes only high school math. If you get to a bit where I mention some math you're less confident of, just search for that term on Khan Academy for a lesson. Or just skip that explanation in the course - it won't stop you from being able to apply the concepts even if you don't always follow the math.
After completing this course (in addition to Andrew Ng's), will I be able to implement state-of-the-art models for real-world problems, where "just ML" (as opposed to Deep Learning) can be used? In other words, would I be competent enough for an entry-level ML engineer position?
Also, the machine learning course was originally the initial introduction for a masters program, so it is a little less intensive and fast moving. But it also assumes a little more math background in parts, since everyone in the program already was pretty familiar with linear algebra, probability, and statistics.
In the end, the two courses go together pretty well, so I don't think it matters too much what order you do them in.
Do you think DL techniques are going to better than traditional techniques for tabular data in the future?
This is in reference to your article: http://www.fast.ai/2018/04/29/categorical-embeddings/ and lessons 3 and 4 from the DL course.
Although decision tree approaches maybe will continue to be faster to train in many cases. At the moment, it really helps to be familiar with both approaches.
Thanks for making this available.
On Udemy, there's a particular course-author I like a great deal (Anthony Alicea iirc) who made a huge difference when I was first learning nodejs & angularjs. Unfortunately, it looks like he only gets to work on these courses here and there - the final project of the Nodejs course has been in-progress for years now at this point.
I can't help but wish that he was able to make more money from these courses so that he would be motivated to develop another 2-3 of them. As-is, it seems like a lot of good teachers end up teaching on a part time basis only (there are some youtube tutorial creators I have in mind here too)
The course I am working on has been in development for over a year.
Quick query - both lessons 1 and 7 are titled “Introduction to Random Forests”, is that intentional?
(In fact, we have a major software release coming up next week - and then nothing planned until well in to 2019.)