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

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.

Great material that's clearly based on valuable practical experience. I and found the "machine learning flight simulator" quizzes to be an educational format. However, the editing of the quiz questions (grammar, matching question types with wording in the question etc) was not flawless in September 2017. This course would benefit from another review pass from this perspective.

This course is clear, and show how a machien learning project should be driven. But there is two problem : First it is entierly theorical : no pratical exercices (so it is only 4 stars) ; second it did not speak of a big problem : How make your boss understand that if you use the "test" set too mush, it become another "developpement" set -> without using sciences words...

Overall, a great course for designing deep learning projects, which gives a lot of insights and tips that typically not taught at university classes. However, there does exist some minor problems related to video editing and quiz problems. I suggest the lecturer or staff of the course put more efforts in dealing with them (and maybe attend more to the discussion forums).

This course gives an overview on how to address common problems faced during machine learning projects. Although these experiences can prove valuable, for average people that may not be actively involved in machine learning, the information may sound like "common sense". The course may benefit with a more abundant set of real-world practice scenarios for analysis.

This course was totally different from the previous two courses. It was focused more on the theoretical aspects of how to approach and build ML projects, difficulties that ML engineers can face and how to avoid them. The content of this course could have been more interesting if more real world problems were included and if there were some programming exercises.

A very nice course to teach how to start a data science project, how to evaluate it, how to select path ahead improving the model, what all to be taken in consideration before training or while training or after training.

Some more case studies could be added since the course is smaller in length and case studies are helping a lot in making understanding clear.

Again, great course. Congratulations. This time, i've missed some programming assignments, although the case studies was very instructive of the practice, some programming experiments with transfer learning will be great. Nevertheless, the course has extremely valuable knowledge to those, like myself, that want to practice in real problems and corporate world.

Actually adds some insights I hadn't learned (or at least I was guessing but it's always nice to have a double check) after 4 years as a data scientist.

Also, some of those insights are very specific to neural networks projects, so doesn't matter how many years have you been working if you've never made deep learning projects this will help you nevertheless.

This two-week course gave very important concepts. However, there's no programming assignments and lectures are lengthy. It felt a little "boring" for a hand-on guy like me.

That being said, one should not skip these important lessons if he/she wants to take charge of ML projects one day instead being a programmer who only takes orders from others for life.

This course gave a lot of practical advice and is excellent material to combine with the more programming-focussed lectures of the deeplearning.ai series.

Small points of criticism are that I thought some videos could have been a bit shorter/less repetitive and there were quite a few language mistakes in the quizzes (missing words and grammatical errors)

Course 3 of the Deep Learning Specialization. There is no coding in this one but longer quizzes which require you to fully understand the concepts and recommendations given in the course. It's all about ML project strategy and how to manage you results and errors. Quite interesting and important for the general understanding of a Deep Learning project.