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

51–60 of 131 posts

Re: Andrew Ng updates his Machine Learning course

#51

Post by thfuran »

londons_explore wrote: post #41
BeetleB wrote: post #14

Earlier quoted context omitted.

The programming assignments in the original course were mostly useless. They provided you with a template with 90% of the problem solved, and you just had to enter an equation to solve the problem.

But you also had to understand the rest of the code in the template. And reading code tends to be a quicker way to learn roughly how something works than writing it from scratch.

Writing code tends to be a much better way of making sure you actually know how something works though.

Re: Andrew Ng updates his Machine Learning course

#52

Post by saynay »

nicd wrote: post #30
smnrchrds wrote: post #8

Earlier quoted context omitted.

What are the others? Any recommendations?

I highly recommend https://course.fast.ai/ . It's much more top down: in the first lesson or two, you train a NN image classifier, rather than starting with first principles and linear algebra. I found this structure to be more motivating and effective.

I went through both, but I definitely think fastai is the better starting point.

Re: Andrew Ng updates his Machine Learning course

#53

Post by AlotOfReading »

londons_explore wrote: post #38
bonniemuffin wrote: post #12

Earlier quoted context omitted.

OTOH, the time I spent learning Octave/Matlab for Andrew Ng's course was 100% wasted time, because I've never used it again in the 10+ years since I took the class, whereas time spent learning Python would've been useful to me in myriad other ways.

It's fairly common I have a little dataset I need to do some fft's on and draw a graph or some other similar one-off task. MATLAB still wins for getting the job done. I wish someone would make "MATLAB with all its toolboxes, but with python syntax, in a colab-like IDE".

Is that not what numpy/scipy with Jupyter (as well as the various distributions that package them) essentially provide? If you just want an all-in-one that has a supported Matlab FFI interface, there's Julia.

Re: Andrew Ng updates his Machine Learning course

#56

Post by no-reply »

lijogdfljk wrote: post #18
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.

I'll ask the opposite question.. how much do these courses cost? Some quick googling has led me to Coursera, but their pricing model seems a bit obtuse. So if they're going to try and grey-pattern me into paying i'm trying to understand how much i would pay. I don't care about a degree from these places, i'd just like to learn. (specifically the crypto course sounds interesting)

Coursera has a monthly $45 fee for the whole specialization. But, the specializations also include a 7 day trial. You get access to all course material and assignments and all courses. Back in my college days(2-3 years ago), I would start a specialization and blaze through in 6-7 days. Money saved and time well spent. Ofc now that I am working, it's not going to be that easy.

Re: Andrew Ng updates his Machine Learning course

#57

Post by no-reply »

lijogdfljk wrote: post #18
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.

I'll ask the opposite question.. how much do these courses cost? Some quick googling has led me to Coursera, but their pricing model seems a bit obtuse. So if they're going to try and grey-pattern me into paying i'm trying to understand how much i would pay. I don't care about a degree from these places, i'd just like to learn. (specifically the crypto course sounds interesting)

You can also purchase an yearly Coursera subscription for $299 or $399 and get access to all the specializations/projects on Coursera for one year.

Re: Andrew Ng updates his Machine Learning course

#58

Post by LosWochosWeek »

bowsamic wrote: post #39
nytesky wrote: post #33

Earlier quoted context omitted.

So sad to hear Mariah disparaged. I’m an Gen X engineer and Matlab is one of our first languages. Use it today still in aerospace but I would imagine Python suits software shops much better. Does Python handle matrix math as well?

MATLAB is still in heavy use in physics, mainly for experiments bc of simulink and the control systems toolbox

I hate MATLAB with a burning passion, but Simulink is a damn good piece of software.

Re: Andrew Ng updates his Machine Learning course

#59

Post by benrow »

mupuff1234 wrote: post #36
UmbertoNoEco wrote: post #25

Earlier quoted context omitted.

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…

> You could use ML in your job/company but then you dont need this course, you just use a ML product. ML product?

For example, Google Vision API can do some out-of-the-box classification on arbitrary images with no training needed. Covers super common cases such as explicit content detection and object detection.

There are more customisable products within Google where you can provide training examples and labels using a UI (AutoML I think it's called). The result is an endpoint you can use to do inference, based on the model created behind the scenes.

I just mention these examples because I've spent a little time researching them at top-level.

Re: Andrew Ng updates his Machine Learning course

#60

Post by LosWochosWeek »

lern_too_spel wrote: post #44
DiogenesKynikos wrote: post #28

Earlier quoted context omitted.

Python is an easy language for beginners, and with numpy, it has excellent support for linear algebra.

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?
Post reply on HN