Hacker News Comments on
Neural Networks and Deep Learning
Hacker News Stories and CommentsAll the comments and stories posted to Hacker News that reference this url.
I finished machine-learning long time ago and it's so good. Look forward to this .
⬐ rg111The only downside of  is that is is taught in Keras + Tensorflow rather than PyTorch.
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...
⬐ rahimnathwaniIIRC you need to pay if you want your assignments to be (auto-)graded.⬐ cheriot⬐ redox99^ this has been the case for other Coursera classes I've done recentlyThat link says "Enroll for Free" and no audit button. Maybe it's because I'm not logged in?⬐ zerkten⬐ rg111Select Enroll and then the dialog has the audit option at the bottom.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. 
⊕ 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.⬐ jklinger410> All videos of all courses in Coursera are free
> There are some great courses in the full free tier as well.
So the full free tier courses offer a free certification? Or else what would be the difference?
I highly recommend Andrew Ng's Coursera courses for both Machine Learning and Deep Learning. Good for beginners, Math is taught along with the course, and gets you a solid foundation:
⬐ hackathonguyThank you! Should I start with the Machine Learning one?⬐ binarymax⬐ dagwAt your level yes, I would recommend starting with the ML course. It is really beneficial to understanding how the mathematics work.
The two most important things to remember, since the courses are challenging: 1) don't be in a hurry, and 2) don't give up! Take the time to learn every detail presented, do the optional exercises, and dig deep.⬐ xeromal⬐ fargoIt's definitely challenging. The math and just seeing the complicated formulas really push me, but the reward is good too. I'm tired of pushing pixels and doing some meaty stuffy like ML is a nice change of pace.I would recommend starting with deep learning first since that's what you are interested in and it covers all the ML principles you need to be familiar with. If you want to go deeper and get familiar with other ML techniques too you can easily follow the old course afterwards.⬐ icc97From my experience Andrew Ng wiped the floor with every other lecturer I've had. Both the ML and his new Deep Learning course.
If the lecturers aren't very interesting Coursera can be as hard as any other lectures. I gave up on the Scala functional programming and disappointingly have stalled with Geoffrey Hinton's Neural Networks courses.
But I really can't understate how good Andrew Ng is, he has a very relaxed manner and manages to make some very complex topics seem almost trivial.
The worst of the mathematics is derivatives and matrix multiplication. You can even avoid matrix multiplication mostly in the ML course, but in his Deep Learning course he takes you through the 300x performance benefit you get from using NumPy and matrix multiplication vs loops.Andrew Ng's courses are excellent. Another pretty good Coursera course is Machine Learning Foundations from the University of Washington. It is very high level and novice friendly. While it covers non of the math and very little programming it does give a nice quick introduction to the most popular ML techniques out there and when to use them. It all depends on what level you are interested in starting. They also have follow up courses that go deeper into the different techniques.⬐ ravishk+1 for this recommendation.
I would specifically recommend Machine Learning Foundations: A Case Study Approach - It is fantastic and helped me greatly start my ML journey last year.
Turi is awesome, I hope Apple is doing something great with it.
You may want to check out Andrew Ng's Deep Learning Specialization over on Coursera.  One of the courses is specifically about hyperparameter tuning and another about structuring your project. There is a lot of practical information scattered across all the courses.
Yes, I'm taking the specialization and having a blast with it. :-)
There are several courses in this specialization. Only 3 are currently available for enrollment right now.
You can get the course material for free, but won't be able to get assignments graded.
Below are links for all of the courses.
To get the course material, you go to each course link and click on "Enroll". Then look for the "Audit" link at the bottom left of the modal dialog that comes up.
If you click the Enroll button on this link you will find the Audit link: https://www.coursera.org/learn/neural-networks-deep-learning
Many weeks end with an interview that might be interesting independent of the course -- the first is a long one with Hinton.
For those who are unfamiliar with coursera or interested in just the videos (and NO certificate) you can enroll in "AUDIT" mode:
AUDIT MODE: http://image.ibb.co/iwm0xF/ng.png
The deep-learning course consist of 5 subcourses:
The deep-learning course is a different course than the prerequisite machine-learning course:
⬐ forgotmysnfast.ai also has a quality ML course⬐ supermdguy⬐ smithsmithI love fast.ai's course, but I also appreciate having a solid and thorough free machine learning course. While fast.ai is good for getting onto the cutting edge of deep learning quickly, it doesn't go through a lot of material that most people in the machine learning industry are assumes to know.Can the certificate be received by completing the course in audit mode and then paying at the end of the course.⬐ flor1sThanks for the links! It seems like you can already browse the lecture videos of the first three courses!⬐ ryanschneiderBTW, if you want to audit, you need to search for each course individually (or click seycombi's links above) and click the Enroll button there, there's no Audit option if you click Enroll on the full Specialization.⬐ jjuelThank you for pointing this out! Was looking for the way to just audit it and could not figure it out.