Great course. I learnt many things like erros estimation and how to think about you ML project. Various data collecting techniques and various methods to reduce errors

Extremely useful practical tips and excellent exercises that can be hardly found elsewhere! Well-structured distinguished content. Thanks for sharing such experience.

The course was excellent. The practical quizzes was very good and it gave a good understanding of how machine learning projects should be built in the right direction.

Great insights on how to structure your project - what to focus on to develop your model - bias, variance, training-dev set and other concepts are very well presented!

One of the most important course for ML/DL practitioner. It provides a lot of useful insights that other courses out there simply seems to avoid or don't cover at all.

The flight simulators are really interesting and generate interest in the field. They also give a glimpse of structuring problems faced while developing an ML project.

Very good overview of the challenges in machine learning projects and pointers to overcoming them. Having these deep learning 'soft skills' could be vitally important.

The advice in this course is worth its weight in gold for anybody who wants to actually practice machine learning. Make sure you go through carefully and learn it all!

Before i come into this class, i have done some deep leaning research and faced some questions in this class, it's a good summary and some strategies are really useful

Again, excellent insights and helpful guidance from Andrew. This course should be taken for anyone who works or is attempting on working with Machine Learning. Kudos!

A course full of tips and knowledge required to build a real world machine learning application. Also help in the starting phase of building a machine learning system

This is a great set of videos that Prof. Andrew Ng transmits his years of experience running deep learning projects through highly valuable insights! Thanks Prof. Ng!

I've gained so much confidence after taking this course. I learnt the thought process behind developing a deep learning project and I loved it. Andrew Ng is the best.

Very practical advices that are typically not offered in academic textbooks. It's invaluable to have Andrew--a leading practitioner--sharing his experience like this.

这门课程不写代码，但是一样精彩，刚好作为后面难度大的 CNN 和 RNN 做一个铺垫。只是我自己在学这门课程的时候刚好赶上学校的课程要写 CNN 的作业，有点急不可耐想跳过去呀，加速播放等。但是静下心来认真学完，还是感觉收获很大，一如既往的精彩。小孩子手骨那块笑尿了，感觉老师像一个天真的小男孩.... 留在党外作用真的更大 :)

Again, it is very good. However, this course is a little bit complicated and abstract in terms of the data obtaining, so may be more assisting details needed. Thanks!

Wonderful course but I think it could be improved adding practical programming assignment in order to test the useful techniques that Andrew teached on this course :)

Love it. Super good to get a feel for the significance of the results and what to do next based on that. Would love to do more of these. As a little snack every day.

This gave me real life insights into selection of Data for training a DL project. Now,I have a structure in my mind to go ahead and strike-start a project directly.

Highly useful for experienced machine learning folks. Given the fact that the discussed issues defined are real-life problems, Data Scientists face in live projects.

Great course! It provides the very necessary non-mathematical details that are important for the success of a project. The content is intuitive and fun. Recommended.

The insights from this modules has made building and deploying machine learning models less easier and less time consuming. Debugging machine learning models methods

I liked this course as it is loaded with information drawn from Professor Ng's experience. With deep learning being a relatively new field, knowing these tips help.

Compendium of invaluable information on practical issues which is unavailable elsewhere. Thank you for saving me from years of suffering to figure out this "wisdom!"

Useful experience from the field, relates pretty well to my experience working on traditional ML projects and extends that intuition to Deep Learning considerations.