Nice.

I wrote down my thoughts after taking his new DL course. Hope it helps you all :) https://medium.com/towards-data-science/thoughts-after-takin...

Excellent review! I haven't taken Ng's original ML course and noticed that you mentioned it would be a pre-requisite to taking any DL course (whether fast.ai or Ng's DL course). Care to elaborate why?

Thanks for this! You just reignited my interest in ML, months after dipping my toes at the end of EDx's Intro to Computational Thinking and Data Science.

How long did the courses take you to complete ?

That's a really good summary. Thanks for posting it :-)

It's still available. I've been taking it for the past month or so.

After learning more about him, he's probably the only person in the world that I envy. I resonate with his ideas a lot, but I'm like 1% of what he is. It makes me a bit sad. I'll be taking his new course as well and hopefully one day I will be able to work in the same field as him.

You should focus on what you can do to make yourself a better person. Anyone on earth can compare themselves to another person and get the sense they feel inferior . Wherever You Go, There You Are.

Yep, it helps to remember that only 0.000000014% of the population is the literal best at anything.

Did you just quote buckaroo bonsai?

Imposter Syndrome is pretty common in CS/Software dev. I try to recognize it for what it is when I feel it and move along.

https://en.wikipedia.org/wiki/Impostor_syndrome

I watched several of the course videos and was struck by how long it's been since college and I did anything with matrices. I kept pausing to go look up what things meant and meanwhile some of his students were catching errors in real time in class

The final project in that course should be using ML to detect every time Ng says "concretely" and compile those clips into a video montage.

Its already done https://www.youtube.com/watch?v=5ZNJPSe1nZs

Thanks for the link to a few concrete examples! :-D

Did anyone do "intuition"?

Abu-Mostafa's Learning From Data[0] was more more rigorous, in my experience. It's a full-fledged Caltech course, sometimes taught on EdX concurrently with on-campus sessions.

The Ng class was a good introduction, but it was mostly applications, not the mathematics and theory behind them.

[0] https://work.caltech.edu/telecourse.html

It is starting again on September 17, 2017 though you can access some of the material already.[1] In addition to the quality of the content, one of the most amazing things about previous offerings is just how involved he has been in the forums, directly helping students.

[1] https://www.edx.org/course/learning-data-introductory-machin...

I took CS221 from Andrew in 2006 (or was it 2007?) Even more has changed since then ;-) It was my second ML course, after taking Daphne Koller's punishing CS229. Right then though I knew ML will sweep the world pretty soon.

Ng famously taught CS229 too, which also looks punishing. Those 2008 videos are available on YouTube: https://www.youtube.com/view_play_list?p=A89DCFA6ADACE599

i thought Daphne Koller taught CS228. probabilistic graphical models. It was very very grueling when i took it in 05.

Daphne has a PGM course on coursera as well. From the half dozen courses I have done on coursera that was by far the most difficult one, to the point where people were talking about making t-shirts stating "I survived week 5". Personally I found it the most interesting and rewarding as well.

Oh yes my bad. I meant to say I took Andrew's CS229, and Daphne's CS228. I never took CS221.

I gave it a try several years ago, but it was very difficult for me to follow. Maybe I should try again...

It's far from challenging. The Stanford one (CS229) is though.

It's not a competition you know ;)

There are two versions of Ng's course, one is on Coursera, the other one taught at Stanford, both available online. Just wanted to point out that the Coursera one is much easier.

The Stanford cs classes on ML and deep learning were honestly surprisingly easy for a Stanford DL class. Or maybe that was because they were good teachers, who knows :)

Maybe not if you are someone lucky enough to have gone to Stanford, and are a CS major.

When I took the ML Class (I also took the AI Class at the same time, but had to drop out due to personal reasons - but I stayed in on the ML Class and finished it), I hadn't really touched linear algebra since high school.

I graduated high school in 1991; Ng's course was 20 years later.

I also didn't have any stats or probability experience under my belt. Nor anything about derivatives or integrals.

I basically had to pick all of this up on-the-fly (fortunately there are internet resources), and even to this day, I barely understand them (I understand matrix operations mostly, but I struggle with probabilities, and I have little-to-no idea on derivatives or integrals).

After high school I went on to get a 1 year, virtually worthless today associates degree from a now-defunct voc-tech school here in Phoenix. Since then, I've been steadily employed as a software engineer here in the valley, and well compensated (I believe) for it. I own my own house, and I have zero debt except for a mortgage.

Given all of that, one should be able to see how such a course would be a challenge. There were a ton of people who signed up, but from what I understand, the majority dropped out after the first couple of weeks. This actually seems "par for the course" though for MOOCs.

I know it was a simplified intro to ML, but for me, it and what I took of the AI Class taught me more than what I ever was able to figure out on my own, especially on neural networks. The light really clicked on for me there. But I was really disappointed to have to drop out of the AI Class.

Later, in the Spring 2012, after Udacity had been established, they weren't able to offer the AI Class as one of their courses. So Thrun came up with another course, which was originally titled "CS373 - How to Build Your Own Self-Driving Vehicle" - and I jumped on that one, and completed it as well. I found it fairly challenging too (but not as challenging as the AI Class was). This course has since been renamed to "AI for Robotics" - which is more apt, I think.

It took a while - but eventually the AI Class was made into a course (I think there was some kind of licensing issue, but I don't know for sure, that was preventing it from being part of Udacity's offerings). I have yet to retake it, but it is on my list (plus a ton of others).

Today, I'm in the home stretch of the 3rd term of Udacity's Self-Driving Car Engineer nanodegree. I'm struggling mightily to get my path planner project to work properly, but I almost have it done (it can make it around the track, but for some reason my behavior planner isn't costing things properly). Got an elective, and the integration project to do, all by mid-October or so.

I don't know if any of this will lead anywhere for me career-wise. I'm happy with my current employer, so I expect to stick around here for a while. I have hopes, dreams, ambitions to perhaps get a degree of some sort in CompSci. I want to really learn more mathematics. I've always been a lifelong learner, but this kind of stuff is really fascinating to me, even if it is (what seems to me at least) complex and not always intuitive. But if it were easy, it probably wouldn't be as fun (but I will say Keras and Tensorflow really make things much easier than when we had to implement a neural net in Octave and Python).

> I'm struggling mightily to get my path planner project to work properly

Having not completed an AI course, I tread lightly.. However, I would guess that this project involves re-implementing an established solution. -- It is work like this that drives me away from such courses; as I can't imagine how creative practices are promoted, instead "correct" techniques are repeatedly hammered in.

> I don't know if any of this will lead anywhere for me career-wise. I'm happy with my current employer, so I expect to stick around here for a while.

Professionals learning to program late in their career typically have a misconception that they're only eligible for entry-level positions in the field of software engineering. Many fail to realize that the 10+ years of experience in their own field can be coupled with their newfound-skill, giving them a background unlike that of many existing professional developers.

Difficulty is subjective

Not if you compare one course to another.

It is if you're comparing them subjectively. Which you are, since difficulty is subjective...