Really interesting!

We used to be concerned about unbalanced train/dev/test, and with this course I realised this are not the main problems for achieving performance in ML

A master class.

Thanks Andrew!

not as technical as the first 2 courses in this specialization (and the next 2 for that matter), but it is still a well rounded course and highly recommend to do all the courses in this specialization!

Extremely interesting and useful practical advice that can help make significant difference when thinking about how to identify and correct problems. The quizzes were fantastic and made me think a lot.

Excellent material. I would say this is the most important course of this specialization. Knowing how to approach a certain problem can indeed save us a lot of time and help us avoid a lot of mistakes.

This course gives great intuitions to develop deep learning model and how to go with deep learning project. I was really impressed and felt like I gain a real experiences without working at industries.

Excellent start for digging into topics that are not taught nowhere else. The author books 'Machine Learning Yearning' is a great next read that goes deeper in some of the aspects, really recommended.

It is good course that gives the practical insights about implementing the machine learning problem. However, it is better to have some coding exercises to be able to grasp the idea more efficiently.

Very helpful tips for navigating possible problems that would likely occur while building/training a model. The "pilot-training" exercieses, that mimick real-life problems / projects, are excellent !

Excellent. Just one remark: sometimes I do not understand quite well the english sens of the sentence. But in overall the course is well structured and I've learned quite a few things in ML Strategy.

Useful to know what are the steps that should be taken after obtaining results. Tho there isn't much information regarding making machine learning projects here (ie. there isn't any hands on project)

I am glad I took this class. There are a lot of things think about with respect to structuring your M/L project. Fortunately, it is not as mysterious as people often claim...but it is very nuanced.

Very important and valuable intuitions about DNN training/optimization. It's full of really practical information while implementing my own models.

DNN을 실제 적용할때 반드시 이해하고 적용해야 할 실질적 내용들로 구성된 멋진 코스 입니다!

It is a special lesson that guide me to think how to build a good model for ML. There is no doubt that Andrew ng taught his project experience without exception and hope that we can benefit from it.

Excellent course to understand the various nuances of structuring these kinds of "projects". Though if the content were presented as parts of programming assignments could have been easier to grasp.

Andrew Ng, awesome teaching technique and well-designed course content make it easier for deep learning beginner to learn how to structure your machine project smoothly and do not lost in a process.

The course was very insightful on how to tweak and evaluate and measure the performance of your model. I loved the course very very much. Hope to see more courses from deeplearning.ai and Andrew.

This course gave some very useful tips on how to start with a Machine learning project when I was struggling to do so. It also gave useful information about error analysis and data set distribution.

I think this is the most useful course in the Specialization. Andrew reveals secrets about details which can speed up working in Deep Learning. It will help to avoid marking time in future projects!

Generally, the course is great. This is a short course and could be combined with other courses in this series. Also, some knowledge such as data splitting has been introduced in the courses before.

The course gives a sound intuition and insight into the parameters to be considered and the crucial thought process involved in making the decisions for improving the performance of neural networks.

Really a good course with mostly the theoretical knowledge on some aspects to reuse your model as well as some error analysis. Thoroughly taught with lots of real-life examples, thanks to Andrew Ng.

It's a great course! This course gave me a lot of new perspectives in constructing a machine learning project. Especially, the discussion of data distribution in the train/dev/test set is fantastic.

Insights distilled from long experience, explained with simple examples. Probably like explaining quantum mechanics to someone who didn't arrive at the conclusion through rigorous first principles!

I really liked this course, such as I liked the rest of the courses in this Specialization. I honestly appreciate that this knowledge is shared, accessible, and made extremelly intuitive and clear.

Really a good course and got an insight into how to structure a machine learning project and some useful techniques for deep learning, such as transfer learning, multi-task, and end-to-end learning