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

121–130 of 131 posts

Re: Andrew Ng updates his Machine Learning course

#121

Post by lern_too_spel »

DaedPsyker wrote: post #27
lern_too_spel wrote: post #10

Earlier quoted context omitted.

The programming assignments were one or two lines in Octave. They'll turn into 10 lines of Python with indentation errors. Python is a worse pedagogical language for any course in applied linear algebra.

I mean python has issues (indentation errors isn't one I would list) but that's besides the point isn't it. The Lingua Franca for ML is currently python. Teaching octave, when most things they search for will be python just seems unnecessarily stubborn. Some day it might be Julia but we aren't there yet.

Indentation errors are a big problem for pedagogy. Imports are a big problem for pedagogy. When you are teaching how algorithms work, you want to implement in a language as close as possible to the language of the domain as possible. Hence, Python is a terrible pedagogical language for linear algebra, and Octave is a reasonable language.

Re: Andrew Ng updates his Machine Learning course

#122

Post by cypress66 »

lern_too_spel wrote: post #121
DaedPsyker wrote: post #27

Earlier quoted context omitted.

I mean python has issues (indentation errors isn't one I would list) but that's besides the point isn't it. The Lingua Franca for ML is currently python. Teaching octave, when most things they search for will be python just seems unnecessarily stubborn. Some day it might be Julia but we aren't there yet.

Indentation errors are a big problem for pedagogy. Imports are a big problem for pedagogy. When you are teaching how algorithms work, you want to implement in a language as close as possible to the language of the domain as possible. Hence, Python is a terrible pedagogical language for linear algebra, and Octave is a reasonable language.

In a vacuum, maybe

But in the real world

1) Python is the lingua franca for ML. You WILL need to learn python. All other resources are in python. Matlab you'll likely never use again, so it's kind of a waste.

2) Probably more people have existing python knowledge than Matlab knowledge. And if you already know python, and you know python is the lingua franca, it's annoying having to learn Matlab knowing that in the real world you'd be better off with python.

Re: Andrew Ng updates his Machine Learning course

#123

Post by _odey »

vasili111 wrote: post #119
_odey wrote: post #21

Earlier quoted context omitted.

Not a full course I'd say, but I've used this one to learn the math behind deep neural networks and code my own from scratch in elixir and C: http://neuralnetworksanddeeplearning.com/

What is required math for starting Ng course?

Can't tell you about Andrew Ng's coruse as I haven't done that, but for Michael Nielsen's course it was Matrices and Partial Derivatives. I'm assuming it's quite similar.

Re: Andrew Ng updates his Machine Learning course

#124

Post by deathtrader666 »

vasili111 wrote: post #120
kache_ wrote: post #105

Earlier quoted context omitted.

If you remember highschool AP math, you're good. Otherwise, check out ISLR for a faster intro, capped by your ability to read

Do you think ISLR is not outdated? I just looked at the date of publication and was wondering if it is still relevant.

Why would Statistics, a branch of mathematics, become outdated in a few years?

Re: Andrew Ng updates his Machine Learning course

#125

Post by FabienC »

jcadam wrote: post #48
bowsamic wrote: post #39

Earlier quoted context omitted.

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

When I worked on the GPS III program back in the day, my job largely consisted of translating scientists' Matlab script into Ada.

Now there's an app for that https://www.adacore.com/qgen :)

Re: Andrew Ng updates his Machine Learning course

#126

Post by saynay »

vasili111 wrote: post #118
saynay wrote: post #108

Earlier quoted context omitted.

I wouldn't say Jeremy is anti-intellectual, but he does know that a lot of people get turned off from the AI field because they are afraid of the math, and a lot of other courses (used to?) start with the math. So he makes sure early and often to tell people that you don't need to understand the math that is happening deep under the hood in order to do productive, even state-of-the-art, research with AI.

What is the required math for starting Ng course?

An understanding of linear algebra and calculus would be useful, but I don't remember it being required.

I was more referring to other resources/classes I had looked at, besides Ng's course or FastAI.

Re: Andrew Ng updates his Machine Learning course

#127

Post by NelsonMinar »

vasili111 wrote: post #116
NelsonMinar wrote: post #47

Earlier quoted context omitted.

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…

Is the knowing only Algebra I enough for this course?

Not the course I took. It relies on basic linear algebra like matrix multiplication. You can probably get through it with just coding and not understanding the math but it wouldn't be much fun.

Not sure about the new course.

Re: Andrew Ng updates his Machine Learning course

#128

Post by lern_too_spel »

cypress66 wrote: post #122
lern_too_spel wrote: post #121

Earlier quoted context omitted.

Indentation errors are a big problem for pedagogy. Imports are a big problem for pedagogy. When you are teaching how algorithms work, you want to implement in a language as close as possible to the language of the domain as possible. Hence, Python is a terrible pedagogical language for linear algebra, and Octave is a reasonable language.

In a vacuum, maybe But in the real world 1) Python is the lingua franca for ML. You WILL need to learn python. All other resources are in python. Matlab you'll likely never use again, so it's kind of a waste. 2) Probably more people have existing python knowledge than Matlab knowledge. And if you already know python, and you know python is the lingua franca, it's annoying having to learn Matlab knowing that in the re…

1. You'll use Matlab in any other linear algebra or numerical methods course as well as in any digital signals course.

2. Optimization algorithms, of which gradient descent is a subset, are deployed in production in many languages, very often not Python.

3. There is almost nothing to learn. For the programming assignments in the course, Octave is used as a succinct DSL for matrix math. The assignments were to simply write the math in a computer and watch what happens when you run the computations.

4. You wouldn't learn Python by completing the programming assignments because you're just calling numerical routines, not dealing with anything else. Writing the code in Python simply adds more opportunity for error with no pedagogical benefit.

Re: Andrew Ng updates his Machine Learning course

#129

Post by DiogenesKynikos »

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?

    import numpy

Re: Andrew Ng updates his Machine Learning course

#130

Post by rashkov »

shankr wrote: post #11
rashkov wrote: post #9

Earlier quoted context omitted.

“Graded assignments and lectures have been rebuilt to teach in Python instead of Octave“

I almost forgot it was in Octave. I had done it when it was offered for the first time by stanford.

I really like the commitment to open source (and student accessibility) that led the course author to choose octave.
Post reply on HN