Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Andrew Ng updates his Machine Learning course

deeplearning.ai

Post reply on HN
Print view View original

71–80 of 131 posts

Re: Andrew Ng updates his Machine Learning course

#71

Post by ghaff »

NelsonMinar wrote: post #47
xwdv wrote: post #15

Although this is the best course on ML, is it really practical for anything? Has anyone built products for things they’ve learned from this course?

I thought it was useful but awfully low level. For example I hope to never, ever implement backpropagation again; I'm going to use whatever code is in TensorFlow or PyTorch or whatever. But as a student I'm glad I did implement it myself, once, so I understand what is going on. More broadly it demystifies the black box of machine learning methods and you can see it for the giant pile of statistical categorizing funct…

I still remember a talk by a woman from Google at a fairly long ago now O'Reilly conference (R.I.P). Part of what she discussed was Research AI vs. Applied AI. The gist of it was that a lot of the things in university course, graduate programs, etc. are tilted towards Research AI and you can get away without a lot of that stuff by using pre-built tooling for practical machine learning applications.

Of course, you want to have some understanding of what's going on under the covers but, for a lot of people, starting from first principles is quite hard and isn't really necessary.

Re: Andrew Ng updates his Machine Learning course

#72

Post by sydthrowaway »

UmbertoNoEco wrote: post #25
xwdv wrote: post #15

Although this is the best course on ML, is it really practical for anything? Has anyone built products for things they’ve learned from this course?

No. The ugly truth is that these courses will be useless to 99% of the people. Machine learning is dominated by big corporations with gigantic amounts of data and processing power. If you want to work in one of them or create competing ML companies you need pedigree (a PhD from a well know university), and those guys arent taking courses with fake credentials. You could use ML in your job/company but then you dont ne…

How about joining FAANG as SWE, and then internal transfer?

Re: Andrew Ng updates his Machine Learning course

#73

Post by ForHackernews »

smnrchrds wrote: post #8
farzatv wrote: post #5

This is one of the best courses on ML.

What are the others? Any recommendations?

"Learning from Data" is outstanding: https://work.caltech.edu/telecourse.html

It's a recorded version of a real Caltech undergrad course, and it's focused on understanding the math behind these algorithms, not just applying black-box ML libraries.

It's much less practical, but I feel like it teaches you more.

Re: Andrew Ng updates his Machine Learning course

#74

Post by klyrs »

LosWochosWeek wrote: post #60
lern_too_spel wrote: post #44

Earlier quoted context omitted.

Octave is an easy language for beginners and has excellent (less ceremony than numpy) support for linear algebra out of the box without having to learn any libraries. The point of the class isn't to teach you how to use libraries but to teach you at a high level how to use gradient descent to optimize parameterized models. Once you understand how it works, it is easy to translate what you know to run well on differen…

What's the difference between learning a library providing functionality versus learning inbuilt functionalities?

Numpy is kind of a funky library with some weird (but good!) syntactic sugar that doesn't translate to the rest of Python. Scipy is a different beast. And pandas. I could go on. Making, and using matrices, feels weird in python and interoperability/efficiency doesn't come for free.

Compare to matlab, where matrices are first-class, syntactic sugar is consistent and rather lovely. But then the rest of the language is detestable.

Re: Andrew Ng updates his Machine Learning course

#76

Post by austinjp »

MafellUser wrote: post #42
xwdv wrote: post #15

Although this is the best course on ML, is it really practical for anything? Has anyone built products for things they’ve learned from this course?

I took this course as a defensive mechanism against BS at work, especially when the consulting Data Scientists were around. In that sense it's super practical. ML is dominated by gigantic datasets and massive computing powers, something individuals will not have a lot of.

Can you explain a little more about how and why this was practical?

Re: Andrew Ng updates his Machine Learning course

#77

Post by rg111 »

dwallin wrote: post #13
criddell wrote: post #2

Does anybody know if it is still free? I took this course and Dan Boneh's cryptography course and both were truly excellent.

They say you can "audit" the course for free, but they employ a ton of grey patterns to get you to pay for it. I haven't been able to find out where to audit it yet. Update: You have to go into the individual courses within the specialization and the enroll popup will have an audit option. First Course is here: https://www.coursera.org/learn/neural-networks-deep-learning...

All videos of all courses in Coursera are free. You can watch them fully without providing your credit card info.

There are two types of courses in Coursera- free and paid.

In case of the paid courses, you can go to the course and navigate to the "Buy Subscription" page and click on "audit the course". You can watch all the videos for free, but you don't get access to quizzes and programming assignments (you never know what a web search will turn up ;)) ⊕. You do not get a certificate by completing a course or completing all courses of a "Specialization".

In the case of a free course, you get access to all the videos, quizzes, and assignments. You don't get any kind of certificate. Instead of going to subscription page, you can just click "Enroll" and choose the no certification option.

There are some great courses in the free tier (videos + assignments, no certs) as well. Dan Boneh's Cryptography and Grossman's Programming Languages A, B, C come to mind. Also Model Thinking by Scott Page.

There were some great discussions on HN in the past. [0][1][2]

⊕ There are courses where duplicates of paid assignments and quizzes are provided under "Practice Assignment" as opposed to "Graded Assignment". Like Martin Odersky's Functional Programming Principles in Scala MOOC.

[0]: https://news.ycombinator.com/item?id=25245125

[1]: https://news.ycombinator.com/item?id=16745042

[2]: https://news.ycombinator.com/item?id=22826722

Re: Andrew Ng updates his Machine Learning course

#78

Post by rg111 »

pm2222 wrote: post #75

I finished machine-learning[1] long time ago and it's so good. Look forward to this [2]. [1] https://www.coursera.org/learn/machine-learning/ [2] https://www.coursera.org/learn/neural-networks-deep-learning...

The only downside of [2] is that is is taught in Keras + Tensorflow rather than PyTorch.

Re: Andrew Ng updates his Machine Learning course

#79

Post by czbond »

cypress66 wrote: post #3

Checked if he moved it away from Matlab, and yes he did! That's what steered me away from his course.

Question: Why was the original version in Matlab? I am familiar with Python, R, and others.... I get that those languages until recently might not have been great over the ancient predecessors (LISP, etc) for ML related.

But I've never seen actual production anything in Matlab. Did Matlab provide something at the time others did not? If so, how did they transfer MatLab to running production models? Or did they create a model with basic outcomes - and then code a representation of it in C++, etc?

Re: Andrew Ng updates his Machine Learning course

#80

Post by rg111 »

jpgvm wrote: post #66
bmitc wrote: post #61

Earlier quoted context omitted.

Can you say more?

I didn't do these particular courses but I found it a lot easier to stay motivated with the top down approach. First demonstrate usefulness, then deepen fundamentals. When I was younger and didn't work full time + have other commitments the bottoms up approach appealed to me more, I think partially because I had bigger time blocks to allocate. i.e I could spend a whole weekend just learning fundamentals of some parti…

Jeremy Howard came off as anti-intellectual to me. He is always like "oh math is nothing... you do not need math... math is not needed" and stuff like that.

Other than that, fast.ai is a great resource, and Jeremy Howard is a great instructor.

You will learn very practical tools and tricks, and a lot of recent research is demystified, but don't expect to achieve deep, general insights.

Also, fast.ai is a very very limited and poor library compared to PyTorch, JAX, TF, etc.

Programming, design, and architecture decisions are outright terrible.

I got paid to write fast.ai in one job. I still have nightmares. I never did it again.

But it is a nice learning resource.

Post reply on HN