Good general introduction to analyzing errors and avoiding common mistakes in machine learning projects and some info on transfer learning and multitask learning. Could've used references for further reading. It should emphasize exploratory data analysis and an ethics review as the start of any project.

4 stars for a very good course that should be improved. Course is still good, but it is not as polished as the first courses in this series. I rated those with 4 stars, too. There are mistakes in the quiz names, grammatical errors in quiz questions, etc. Never-the-less, it is the best of its kind.

Good course helped a lot to gain insights into the problems of machine learning but I would say more exercises are needed even if these guided exercises are good.

maybe add an exercise where you can simulate a fake NN and get the result and then choose what to do to get a feel of what you should do.

Interesting insights.

The insights could be visually structured a bit better so that I can also check them after the course as a reminder.

Often recommendations like if then could be put in processes or cheat sheets

overall: very valuable course regarding the insights and encouraging style of Andrew Ng

Well structured course, Andrew always never lets down your expectation, the explanations were very clean with the best appropriate examples to suit the explanation. Being more of theoretical, the task of giving us the correct intuition is really well handled by the way the lectures are structured.

Instead of clearly and concisely formulating some of the ideas (like F1 formula for the metric), they are discussed as if they were hard to understand. This makes the understanding harder and is rather annoying. The assignments are useful - they make sure you understood the material the material.

This was a good intuition course. I learned a lot and loved the content. However, I am afraid the information here needs to be repeated many times to make it a habit (as part of programming exercises). That's why I am giving it a 4-star. I feel like this could have been part of the last course.

Great overall. However, a major thing that is missing is the different between val set and dev set, and about the recent trend to perform K-Fold CV on the training set to get the val set. Maybe still need a separate dev set because of the different distribution if it comes a separate soure?

Wish there were more projects / assignments to exercise concepts taught. Like in the first 2 courses of the specialization.

Maybe even blending videos with a broader Jupyter notebook would be better. The videos are great, but paired with practical application its much more likely to stick.

-This course have two quizzes and no programming assignment.

-This course gives a very good advice on how we can improve Algorithm performance.

-Best way to split data into Train/dev/test.

-Quizzes statement can be made more precise and clear but stil the scenario in the quiz was good.

Very good course, but in contrast to the other courses the practical exercises are missing. I would like to see some transfer learning and (non-)end-to-end learning approaches, where the student has to examine how bad/good end-to-end performs in contrast to a multi-step approaches.

The content of this course is quite unique. Thus it makes it much more interesting and important.

Thank's a lot for this tips!

However it would be nicer if there is some videos practical assignments about tech aspects of implementations of "transfer learning" and "multitask learning"

A very nuanced course, which I see myself coming back to, gaining more insight and appreciation for it over time. Some of the quiz questions where quite difficult to answer as they were open to interpretation. I think Prof. Ng went the extra mile in putting this material together.

I got the same feedback for many of my colleagues that this course is not that important and I should start with course #4 instead, but I am glad I didn't there is a lot of insights and experiences in this course that I think it would take anyone many years to conclude by himself.

That's a great course to learn some practicalities of deep learning/transfer learning and multitask learning, and when to use different strategies for structuring a project. In my opinion, the course could do with a hands-on programming exercise to help consolidate the learnings.

Sometimes its become bored who has not any experienced into working on real life ML project because without facing problem you can not understand problem in better way so i recommend course instructure to make this course with little more practical way so that it easy to digest.

The lack of progamming assignments hurts what could have been one of the best courses of the specialization, especially in solidifying the advices and ideas seen here. Nevertheless this course still provides valuable informations, and it's one i'll come back to later for sure.

A bit slow going and repetitive (and some simple video editing to remove double sections would improve things). Nevertheless I'm amazed how much I learned or consolidated is just a few evenings of watching these videos. Thanks again! Looking forward to course 4 in this series.

Thorough and practical guidelines to structure and analyze issues with machine learning projects. Distilled learning presented from a lot of project experience. It would be hard to gain such knowledge without having gone through a number of projects. Accelerates your learning.

It was a very informative course. I learnt about different metrics that are used for measuring the success of deep learning models . I learnt about the different approaches like transfer learning, multi task learning etc. The assignments were very challenging and interesting.

Machine learning simulator assignments were great, wish we could have more of them both in this course as well as in the other courses in the specialization. Additionally, I would have loved programming assignments that reinforced these largely workflow-related concepts.

Useful knowledge regarding the efficient practices in the application of machine learning. Mentors doesn't seem as responsive though, compared to the other courses of the specialization. Quizzes were helpful, but needs more justification for some of the correct answers.

The course showed the experiences while dealing with machine learning projects but could have been better if the experience would have been shared through practical exercises rather than objective case study.

It would be better if there were programming exercise as well.

I have a feeling that this third course is not yet fully edited. I see some black screens, and sometimes the clips have Andrew speak faster than usual. Nonetheless, the various tips and appropriate actions to take when doing a machine learning project were very useful.

Good explanation for the initial steps of organizing the ML project and the direction to approach the problem accounted for. The quiz was interesting but as it is the same set of questions for any next attempt, I would not say I have mastered the course completely.