This course was less satisfying then the 2 previous in the specialization. A lot of repetitions, no programming exercices. Interesting test cases but feels a little out of scope because we have not done image and speech reccon yet. Consider putting the course at the end of the specialization maybe?

I think the week 1 was overstreched. There was not much content to deliver and for the first time Andrew's classes made me sleep. It was like the boring lectures we get at school. I think we can easily shorten the length of this course or just scrape it and add it to course 2.

I found this course to be a bit confusing with regards to what data set (training/dev/test) to fix under what conditions and so on. I've also missed having a practical home work, the case studies were fine, but I find that practical applications help me remember things better.

Some of the quiz questions (especially in the first week) were quite ambiguous. If I did not take the quiz directly after the videos, I don't believe I would be able to pass, Also some written summaries as in the 1st Ng's Machine Learning course would be helpful.

Some helpful advice here and there, but a lot of it seemed like common sense. It was not that difficult and a tad boring. Would maybe benefit from having us do actually data collection and cleaning tasks, or implement a ML pipeline and monitoring for the pipeline

Generally provides very good advice. Perhaps this course better placed at the end of the course as there isn't much hands-on experience involved and students would benefit form having experience with CNN's and RNN's prior to thinking on project-level scales.

Too many broad statements of "yeah, we generally do this thing for best results" with very little explanation of the background theory. I don't expect advanced math and derivations, but better intuition into why certain best practices exist would be nice.

This course was good, but it was pretty light on content to be considered a separate course by itself. Though the content is valuable, it could've been included as additional/bonus content on either of the first two courses in the DeepLearnign.ai series.

I didn't find this course as engaging as Course 1 -- there weren't any coding exercises and it felt like a bit of a let-down after the excitement of coding in Course 1. But it may turn out to have value when trying to start a new AI project from scratch.

This course felt a bit "padded" compared to the previous ones. Also the lack of programming exercises made it seem more theoretical. Finally, the material seems rushed, e.g. there are mistakes in the video editing, strangely long pauses by the teacher.

Many helpful insights and advice from an experienced person is always great, but I don't thing this can be qualified as a complete 'course'. As I now see it - Course 2 and 3 of this specialization could easily be merged into one without loosing much.

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