The course should have had at least two more quizzes to understand the content better. Also, I would suggest adding programming exercises that help to better explore the ideas of orthogonality, train-dev set correction, and data synthesis.

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.

This course to me seemed a bit too much theoretical.This could have been a little more assignment weighted so as to bring more focus to study and practise.Overall the case studies were pretty thorough to cover the course material.

I think that a lot of this knowledge would have been useful had it been given after building a few projects ourselves (i.e - sample projects), I could not feel connected with the content much and was a little uninteresting for me.

The course must have had some coding exercises showing how wrong the error analysis doesn't work and also some exercises on transfer learning, multi-task learning in order to see in practice how these concepts work in real life.

This course did not really feel like a course, just videos and ambiguous quizzes. Some repetition and poor editing of the videos. I recommend to reformat this course to be more substantial and to include programming exercises.

Compare to other courses of the specialization, this has lower quality of video lectures, often repeats things from previous courses and I think it would be better to separate whole course as a separate week of a previous one.

Very interesting course about guidelines about how to set up a project target oriented, not so trivial. Perhaps an improvement could be to add a chapter on the various DN architectures available for the various tasks.

Would be much better if it included a programming assignment as a final project. I'd like to have a little less scaffolding during the decision-making process to see how well I can do on even more realistic problems.

It is a good course because it highlights practical aspects of implementing ML. Some of the test questions were a bit ambiguous though.

I'd also like to have seen Transfer/Multi-task learning implementation exercises.

I understand why this course is important, but for me it was the least favorite course so far. Some of the videos were too long and repeat themselves. Maybe it's because I have knowledge in machine learning already.

This course is full of intuitions that are very difficult to remember at once. The quiz is very hard and mind teasing. For better confidence, I would like if you add one more case study.

In general the course is good

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.

Good course to learn about structuring the projects and carrying out error analysis. I wish there were some assignment to work on in addition to the case study quizzes. Assignment really help us learn effectively

The course was just a bunch of tips and suggestions. Yes, they are useful, but given the empirical nature of machine learning I would expect those tips to be accompanied by practical applications and homework.

I expected more. The videos were a little long and repetitive. The content was important, though. Maybe the course materials could be squeezed into one week and combined with the previous deep learning course.

THe course was challenging and had valuable inputs. But it would be even more wonderful if we got to work on some portion of the case studies as a capstone project at the very least. Else Its a 5 star course.

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!

The quality of the course is not up to par with the other courses in the specialization. There is very little content and it is gone through too slowly. There are also more bugs and errors in the exercises.

Most of the materials in this course is tedious and have already been taught in previous courses. But I suggest the Transfer Learning and Multi-task Learning part, as well as the end-to-end learning part.

The course was misleading on what homework there was (machine learning flight simulation?) There was no homework. and the lectures were pretty bland compared to other courses in this specialty.

Transfer Learning and Multi-Task learning discussed in the course would greatly benefit from having programming assignments where people can play around with the data and learn confidently.

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.

Not as helpful... just a few suggestions and ideas... but there's no great application of the information learned here like a walk-through project or something with code, that's graded.

less useful than previous courses.

Would appreciate to go much deeper in directions like CNN, RNN, RL and review Unsupervised Learning (which was too light, ... no mention about RBM)