Nov 23, 2017
I learned so many things in this module. I learned that how to do error analysys and different kind of the learning techniques. Thanks Professor Andrew Ng to provide such a valuable and updated stuff.
Mar 08, 2018
Going beyond the technical details, this part of the course goes into the high level view on how to direct your efforts in a ML project. Really enjoyable and useful. Thanks for making this available!
por Matías L M•
Oct 30, 2017
Really bad course. Even the professor does a good job at explaining everything, it does not seem to be a technical course :(
por Viliam R•
Oct 21, 2017
i missed practical (programming) assignments here. quizes are great, but could never substitute for getting hands dirty.
Apr 08, 2018
por Marina R•
Oct 18, 2017
I found the course rather confusing than helpful. One of the key issues with video-only courses is lack of interaction of the user with the material. In previous Andrew's ML courses, this issue was cunningly tackled with "wake-up" multiple choice mini-quizzes. Such techniques would help the course a lot.
The questions in the exam were poorly phrased and full of typos; some had numerical issues (percentage of errors in the dev set did not sum up). Some of the answers seemed to contradict with the material as I remembered it from the course: f.e., the question on whether to get more foggy images to improve the model performance should have been answered with "augmentation is fine as long as it looks fine to the human eye". This contradicts to Andrew's remarks in the course video "Addressing data mismatch" video -> Artificial data synthesis. Are you sure we would not introduce a bias by adding artificial fog to frontal camera images?
por Nikolay B•
Oct 26, 2017
the best course in so far, not that much theory but a lot of "insides" from the field. However, still no practice, Im studying for 3 month and still have no idea how to create a real application.
por Mohamed E•
Nov 23, 2017
Not much to learn in this course, basic recommendations can be condensed in one or two lectures
por David L•
May 23, 2018
Zero programming assignments, but simple quizzes that will make whatever you just learned as fleeting as the morning dew on a hot summer's day. Too bad, because otherwise the material is quite interesting.
por Mikael B•
Sep 13, 2017
This course had a much less ambitious scope than the previous two courses and I think that the programming assignments are very important to help me learn properly.
por Chaobin Y•
Oct 12, 2017
Too little materials.
por Christof H•
Sep 18, 2017
por HAMM,CHRISTOPHER A•
May 07, 2018
I need a lot more practice than is offered here. I would also strongly prefer if the instruction followed some of the best practice laid out in books such as "How Learning Works" because I have difficulty following the instructor's line of reasoning.
por Mads E H•
Oct 26, 2017
Not applicable enough. I think you need more tooling around DL before these meta lectures makes sense.
por Artem M•
Apr 24, 2018
Too much information in too little time. Additionally, all information is mostly practical, and having no real exercises makes it hard to remember all the details.
por Markus B•
Sep 06, 2017
Just a few videos without any programming excercise or a bunch of rather broad statements that are not really tried out in programming examples are not really worth the money and more importantly the time. The first two courses are good, this is definitely a drop in terms of quality. This one needs more meat on the bone.
por Daniel S•
Mar 20, 2018
Definitely not worth paying for (and I literally completed this in one afternoon). Thankfully I did not pay, so it was not that bad value in fairness.
In honesty the lack of value from this course actually says a lot about Andrew Ng's original Machine Learning course, which was consistently excellent. Actually coding in Octave for that class cemented a lot of concepts as well, which this course does not.
The title of the course suggests this is pitched towards more advanced students who already know about Machine Learning but maybe not so much about best practices. This feels far too basic for that demographic. The practices are sensible though and useful, if maybe overly focussed on massive datasets as opposed to the ones that Google *doesn't* deal with on a daily basis. Things like SMOTE could have been mentioned as well, for example.
TL;DR: This feels like a missed opportunity. My advice is don't take it if you've done Andrew Ng's ML course. Google things after that and wait for a decent course that's pitched towards intermediate students.
por Younes A•
Dec 07, 2017
The material is great, but the production quality is so poor that I had to give 4 stars only. Videos have blank and repeating segments, and more quizes have mistakes that make getting a 100% because you know the material impossible (you have to tolerate some wrong answers to do it). This means you can't rely on quizes at all, because maybe the ones you got right were actually wrong :). The ones I got wrong were also called out by other people on the forums, so I guess maybe I am right.
por Saad K•
Sep 12, 2017
I found it quite verbose... Could have easily been shrunk and fit inside the other course... Don't think it needs a separate course for this
por Ted S•
Dec 19, 2017
Doesn't look like it was checked for quality control (e.g. Videos with bad takes), Ng rambles sometimes so that it seems as if he is filling time, there are no knowledge checks. This course wasn't ready. Case study flight simulators are good, but poorly introduced.
por Vishal K•
Dec 17, 2017
The weakest of the three so far - comparatively lots of fluff. Unclear definitions with lots of perhapses and maybes.
por Alexander V•
Feb 25, 2018
A lot of very common-place suggestions that could just as easily be conveyed in a third of the time.
por 태윤 김•
Jul 09, 2018
por John H•
Sep 21, 2018
Poor video editing. Not enough graded material to feel confident that I fully understand the concepts proposed in the lectures. Definite step backwards from courses 1-2.
por Subhadeep R•
Sep 25, 2018
Frankly I didn't find this to be very useful.
por Ashvin L•
Aug 25, 2018
The 3rd course is more art than science. There is a lot of breadth, but we cover each topic in passing. Therefore, from a student perspective, I find that the concepts are not cemented and it is entirely possible that I forget them once I move on to the next course.
The second issue I find with the course is that there are no programming assignments. Programming assignments. Programming assignments are key to understanding such complex topics and getting the idea cemented. It would have been much better, if we could cover each topic such as data-mismatch, comparison to human level performance, etc via assignments.
por Sreemanananth S•
Oct 01, 2018
Very verbose with hand-wayy examples. The 18 minute lecture was the hardest Ive tried to not fall asleep. The second quiz has extremely badly written questions with multiple choice answers. Very ambiguously worded QnA. Don't mistake this review for the whole DL specialization though. Andrew's DL specialization course is brilliantly structured and an excellent primer for folks such as myself just getting into DL. It is only this section on structuring ML projects which is a little bit of a drab.