糖心vlog官网观看

Not that good.

to theoritcal

too much bugs

No Homework!

Bit tedious

Bit boring.

A bit short

Too simple

Too short.

Knowledge

too easy

Too easy

useful

good

Good

okay

甏涤爱鞚�

ich

k

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.

Notwithstanding the great video lectures this course's assignments were poorly composed:

Firstly, there are no programming assignments! I understand the material here is mostly conceptual, however subjects such as 'Transfer learning' and 'Multi - task learning' should be given as a programming assignments. In 'Transfer learning' you need to modify an existing model, which I think is a good tool for a student. Hopefully we will use it in future lessons. Lastly some of the questions in both 'quizzes' have many complaints in the forum and the same complaints reappear yearly, therefor it's a bit annoying no measures are taken to modify the questions so they will be clearer.

This course was pretty poor. Too many of the lectures are repetitive, and the examples given to discuss the concepts seem overly simplistic. It would be far better if AN actually discussed previous cases and what pitfalls to watch out for. For example, it's useful for practitioners to understand human component features that he mentions. He's probably seen a lot of instances in which engineers came up with great ideas that ended up differentiating a mediocre-performing algorithm from a far better one. He could also discuss go into greater case study detail of instances in which transfer learning/muti-task learning worked well or not.

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.

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.

This course is just a set of (perhaps useful) advice on how to make decisions when working on a project, not a course on techniques or how to actually do things. There are no programming assignments as in the other courses of the specialization, just some "decision making simulators". I learned more and enjoyed more the other courses. It feels like all these advice could be given as part of the other courses. (But perhaps I am much more technically inclined.)