This course is more about explaining how to set your analysis universe(train/dev sets etc.) and where to go when u hit a road block i.e. when to concentrate on bias/variance etc.

Suggestions: Unlike other courses, no programming assignments here .. may be some programming assignments + Quiz in a case study format would have been more helpful. E.g. present a case, ask the student to write piece of code to calculate bias and other metrics, and then ask questions from the metrics derived instead of mentioning directly the values for human level error, Bayes estimate.

This is a great course, something I will keep coming back to even after I'm done because it talks about strategy and rules of thumb re: Machine Learning/ Deep Learning approaches. It introduced me to certain concepts that were brand new for me and that was a great outcome for me. I wish the audio was better and the notes were better because writing on the small screen really hinders expressibility. I would rather have Dr. Ng write/draw on a chalk board than the small screen, I feel it really constrains his process. Still it's a great course!

A very quick course (significantly faster to complete than the preceding two courses in the specialization) that is usefully targeted at the practical aspects of how to go about developing a neural network. Prof Ng sets out a clear and logical approach to building, diagnosing issues, and iteratively improving models. The one critique I have is that a few of the topics are repeated from things already covered in the earlier courses and the editing of the videos is not done quite as well. Still, a very worthwhile use of very little time!

Very useful tips and insights on how to approach supervised ML projects. However a more in-depth case study would be interesting, to try to answer questions like: where does easily-available input data come from ? (sure CCD cameras & other tech, but but do not forget all those little labelling hands ^^) what makes the success of hand-design features in such or such domain ? can we bootstrap ML back into tools that help with valuable hand-design ? can unsupervised learning help with cleaning up input data for ML ?

The course content is very instructive and will greatly improve your performance on real world machine learning projects. Basically, this course gives you recipes to improve the performance of your model when something is wrong in your data and if you have not enough data.

Compared to the first two courses in the deep learning specialization, videos were a bit of lower quality, not completely edited and the course could have featured programming assignments, notably on transfer and multitask learning.

the pronounciation of the presenter is increasingly difficult to understand. Some things are endlessly repeated. The videos have big editing problems. -- Overall it pretends to instill some wisdom on the learner, which is completely misplaced given the audience of this course ... much more real world experience would be needed here. From the perspective of a beginner, this was very theoretical and probably already forgotten before it becomes useful in real life. Not a fan of this course at all.

The course is absolutely fantastic, Andrew is a fantastic lecturer, however I could not give it 5 stars as there were parts of the videos which had not been edited well. There are parts where Andrew pauses and repeat himself again which seems intentionally done to allow the editor to appropriately remove the stumbled sections and make the talking seem continuous, but editing these sections has been overlooked. Its a shame as its a slight but noticeable issue in an otherwise flawless course.

The course content is very interesting and opened my eyes of different strategies to improve the results of a Machine Learning project.

The recommendations also helped me greatly to dispel some of the myths and bluffs that run rampant in this developing field.

It makes me a better engineer. On the minus side, the course is not as polished as the two previous ones and some edit could help to cut in the content that is repeated.

Other than that, some great ideas and I am glad I took it

I liked how the course gives such insights that would help in progressing efficiently with a DL project in hand. This is the kind of thing that one needs to know about in addition to all the technical aspects.

I think the course would benefit from even more examples where a concrete project is examined and the student could see how the team was progressing: what were the iterations, what challenges were resolved, what were the intermediate results and of course: the final result.

The course gave an extremely wholistic insight into what applying deep learning theory may be like in a commercial context. It felt as if Andrew left no stone unturned, answering every question a student could have either in the video, or in the weekly quizzes. The only adjustment I'd have liked to see is Andrew spending more time elaborating on multi-task learning networks (such as how to initialize back propagation along a network which uses multi-task learning).

Liking this course is subjective. It is indeed based on the experience of others, but since experience can't always be generalized and transferred, the lectures are repetitive and bland (they are also badly edited in Week 2). On the other hand, the two "ML flight simulators" are really interesting and answering them is not obvious. It requires a lot of thinking and focus to choose correctly from apparently equivalent solutions, which might happen in real projects.

Course was very theoretical as compared to the previous 2 courses in this specialization, and maybe a programming assignment could have been included (optional) where in the student could maybe learn how to play around with distributing the train/dev/test data and calculating the errors. Personally since I like hands on stuff more, these are my two cents on what could have been better :) amazing work by the teaching team and others on the backend as always!! :D

Once again, Andrew bringin' the heat!However, I docked a star for a couple of reasons. First off, I feel like there could be a bit more material here, perhaps an example notebook with noising and illustrating avoidable bias / variance / data mismatch.Most importantly though, I strongly, strongly recommend you go through the Week 2 Quiz (Autonomous Driving) and double check it for spelling/typing errors. There are quite a few of them!

Great practical advice on actually structuring and implementing machine learning projects. However the case study approach is more useful for people already in the field and working on projects than for some of us who are not yet in the field but attempting to gain exposure and knowledge in Machine Learning. I guess the value of these case studies will be more apparent when I actually start implementing ML projects in the real world

I find this course very relevant for practitioners. Perhaps from a team/organizational point of view it is the most relevant course. I agree that the concepts presented essentially distinguish the great from the average developer team. However, some of the material is very practical and I feel that right way to learn it is by doing it. To be fair it is very difficult to reflect that in a course! Overall I think it is very useful.

Hi, This course though very useful had become a bit monotonous and at times a bit difficult to understand. There could have been better presentation giving more examples. The Quiz had really tough questions , in some cases the language is not clear. I request the course mentors to look into the same. Nevertheless, it has definitely been very useful as it highlights the practical problems faced and ways to resolve them

Very good course overall - I wish there were some coding assignments or recommendations of projects to try on our own to test the knowledge for each lecture. I noticed one inconsistency in the second quiz: question 7 in one of the versions says You have finally chosen the following split, and in the answers they talk about whether the friend is wrong or not, while it has not been mentioned in the previous questions.

This Course offers simple, useful and general tips for starting a typical deep learning project. The most valuable part is on how to split datasets and how to identify possible data distribution mismatch. The tips and case studies do not always work in real application. But that is perhaps because the course is intending to be simple. This course does not require any math backgrounds and can be completed in 4 hours.

Although I see other learners saying that this is the worse of all the Deep Learning specialization courses because there are no programming assignments, I believe it was a very useful course full of practical knowledge for properly structuring ML projects. I agree, however, that video quality is worse that the other courses and there are some editing issues (some video segments repeat, blank sections, etc.)

This course is hard to complete because the lessons are very large and difficult to understand. However, I recommend this course for anyone than want to apply deep learning in real enterprise world.

Este curso es dificil de completar ya que las lecciones son muy largas y costosas de entender. Sin embargo, recomiendo el curso para todo aquel que quiera aplicar deep learning en el mundo empresarial.

I like the explanation and the scenario, but I miss the implementation.

If you add some real implementation about transfer learning using a framework like TF (MobileNet) or PyTorch, that will be great.

I hope you can improve the transcript (Arabic)

I found many times it looks like you are using Google translation. Please give in each class the operantly to correct the transcript.

Thanks a lot

I liked this course a lot, since it introduces transfer learning and multi-task learning and so moves you toward more powerful and realistic AI applications than the previous courses in the specialization. However, I missed the programming assignments that aided understanding so much in the previous courses. The quiz by itself was not as effective at illustrating the key concepts.

I wouldn't really consider this a "course," but the stuff he taught was great. However, Andrew could go much deeper into these topics. Some real data examples that he has come across would be even more helpful. Seeing how he codes his approaches in python would also be a very useful (and quick) batch of lectures. If he needed to extend it another week that would be understandable.

Excellent course just like the previous two. Short programming exercises would have been nice to have. Some of the answers in the quiz were too similar and this might be quite confusing for non-native English speakers and therefore can reflect more knowledge in English language rather than knowledge in related machine learning topics. I am looking forward for the next 2 courses.

This could be a more useful course if it came after convolutional neural networks and sequence models courses. In that case, the learner could practice some of the strategies on the models that he had previously developed. Right now, most of the strategies will be forgotten by the time that the learner reaches to a point that can confidently develop large deep learning models.