Old ML course by Andrew Ng vs the new ML Specialization

Course Q&A Machine Learning Specialization Supervised ML: Regression and Classification
1

Hi everyone.
I have been taking the old ML course by Andrew Ng on Coursera for a while and I had advanced to week 4, but I have decided to switch to the new course. It seems to me that the first course of the specialization covers almost the same topics as the first 3 weeks of the old course. My question is, should I advance to the second course of the specialization, or should I start over with the first course?

And how much Python knowledge is required for taking the first course? I mean, is there any Python taught during the course? if so, what topics are covered? I have some prior knowledge of coding with Python but I am not familiar with NumPy and Pandas. Should I learn them before starting the course?

2

Hey @Sama_san,
Welcome to the community. I haven’t done the original ML course myself, so, I am not really familiar with the extent of over-lapping between the original course and the new specialization.

But if you feel that they have over-lapping content, then I think that you can easily complete the first course in a matter of days. This will also help you to revise your foundations, and if I am not wrong, Course 1 is filled with optional labs, something which was missing from the original course. Additionally, completing course 1 will help you to get up to speed with Python, since the original course was not served with Python.

For this, check out 03 of this thread.

As to this, it really depends on you how you want to proceed. If you want, you can go through some of the tutorials of these packages before you start with MLS, and it is most certainly going to help you. You can also start with MLS and check out these tutorials as and when you need them, and this strategy is perfectly fine as well. You will find that the MLS labs provide links to the documentation whenever a new function is used from these packages.

I hope this helps.

Cheers,
Elemento

1 Like
3

I’m also a mentor for the original ML course.

This course adds a few new ML methods (decision trees and reinforcement learning, for example), but does not include some material from the original (no SVM or PCA).

One benefit of this course is that the videos were recorded recently, and Andrew has had lots of practice at presenting and improving this material (since the original course was recorded some 10 years ago).

And of course the programming environments are entirely different.

So it doesn’t hurt to complete both courses.

Both courses have the same philosophy about your programming expertise - you’re expected to be moderately fluent in programming in the appropriate language.

Personally I think Octave/MATLAB from the original course was much easier for novices to use. Python is no picnic if this is your first programming rodeo.

2 Likes
4

Hi. I´m trying to pick up Andrew´s original ML course where I left it four years ago, while starting the new version on Coursera. But I just can´t find a link to the original course. Can you help me on that? Thanks a lot.

5

In the URLs, where it currently says “machine_learning”, edit those URLs to be “machine_learning_course”.

6

Which URL’s you’re referring to ?.. In Coursera?
Many thanks for you reply !!

7

I mean all of the URLs on Coursera.

This takes you to the Machine Learning Specialization, C1 W1:
https://www.coursera.org/learn/machine-learning/home/week/1

This takes you to the start of the original 11-week “Stanford ML” course:
https://www.coursera.org/learn/machine-learning-course/home/week/1

Notes:

  • The original course lesson numbers are now “modules” instead of “weeks”.

  • The original course has been deprecated for a few years, and is no longer being supported or maintained. It uses the Coursera discussion forum.

1 Like
8

GREAT !! Thanks a lot! Exactly what I was looking for to bootstrap and resume my learning and catch the wave. The original Andrew course in Course has even saved my progress at the time I left.

9

If you want to catch the wave, I recommend you enroll in the new course. Octave and MATLAB will not get you very far in the current field of ML and AI.

10

@TMosh I think one of the difficulty with Matlab what I found were people struggle is that it is a licenses software and require toolbox dependency. On the other hand when we talk about the Octave (it is an open source) but it has some limitation when compared with the matlab.
However, I have seen lot of change from R2022 to R2024 in Matlab version. As they are updating them in each version and making user of python to run the python code on Matlab itself. .

11

I’ve been a mentor for the original ML course since 2015.

The biggest drawback to that course was that it relied on students to install their own toolset.

The mentors could not be experts on fixing installation issues for every individual student.

Given the huge number of operating systems and computer types, and each individual’s skill at fixing IT problems, some students were never able to make progress in the course at all.

Late in the course history, MATLAB started providing a free online license. That helped considerable. But since the course was deprecated a couple of years ago, MATLAB no longer provides a free license.

1 Like