Comentários e feedback de alunos de Structuring Machine Learning Projects da instituição deeplearning.ai

not that useful i thought

Okay, but lacks practicality

nice lectures and very useful knowledge learned by Andrew, but it is really short and no working assignment through real code.... and quite a lot more mistake than course1 and 2. Really love the two previous courses, don't work why the quality of the course drop off so sharply.

Somewhat disappointed, but still really great lectures.

Not nearly as good as the first two courses. These two weeks should probably be added into the second course at some point...

I fear this material won't challenge many learners. Feels like review.

I'm grading this course lower than I graded the two previous ones for two reasons: 1) while there are many examples given in the course, it is actually hard to take a step back and see how to concretely achieve some goals in a more generic manner, and 2) in the assignments (which are made of quizzes), many "wrong" answers would actually be appropriate if more context was given.

ich

I wished there were exercises besides the quizzes in this course

Overview of the machine learning process. No projects or sample code to actually organize the ideas into code.

Learned new things but the course was boring.......

Good information about how to structure projects and how to boost performance. Not very hands-on however. Fits in well with the Specialization though as a break before CNN's and sequences.

Wordy and too abstract without hands on experience.

Some interesting information in week 2 where multitask learning, transfer learning and end-to-end vs sequential nets are discussed. The bit on breaking down your errors into classes will also come in handy!

Week 1 was quite repetitive and seemed to be mostly common sense, probably could have cut these videos in half without losing much. Personally I watched most of this at 1.5x speed to avoid falling asleep. First quiz also had some less then conclusive answers - there's a lot of disagreement in the forums! Some issues also with the cutting of the videos, those these are only a minor nuisance overall.

Overall, less impressive then the other courses but still useful knowledge can be obtained here.

From a philosophical standpoint, I especially liked the 2 interviews in this course.

No Homework!

Was really enthousiastic about the first two courses in the specialization, the third however felt a bit like going back a step in level of advancement.

Informative but too short

not as interesting as the other courses

Videos are quite long. Good course although a bit heavier than the previous ones

Good for the numerous hints about practical issues such as different distributions on train/dev/set. Very bad for the lack of hands-on assignments. Good practical advices but no occasion to see them working!

Video lectures tend to be repetitious, and can be confusing.

I got an intuitions from this lectures. But What I want to get from this lecture when I first saw the title, is the method how we can define the activation function at multi-task learning etc. In this video, I got only the overall flows.

Interesting and practical information, but it felt stretched out in an attempt to create a two-week course. With some editing and less repeated information this could be one week that would fit in the prior course.

Kinda boring, but still pretty practical.

Good non-technical materials, but short enough to be incorporated into other courses. Some aspects feel subjective. Many typos/minor mistakes in quizzes

Good general information is provided but this material could be layered into the other courses in this specialization. I would recommend that the case studies be based on real industry problems that present the backstory of the decisions the teams made. Also programming assignments would be useful in which the impact of incorrectly classified training data is studied in detail or in which images that have been synthesized are used versus not used. It did not take too much time to work through this course so the information provided is worth the cost, but I am not convinced that this series is viewed as more than an opportunity to make some money off of the name brand. Much of the information provided so far is covered in the Deep Learning - Goodfellow text and the extras are vague and repetitive.