Helpful context for a person such as me who is changing careers to the Data Science field. Would be easy to focus only on the mechanics of ML/DL and ignore the broader context of how to really pull a ML project together and make the effort effective.

This part of the course is really unique and provides an understanding of what are the challenges that you could as a Machine Learning engineer. The problem of the exercise was really great in terms of planning and execution of the real-world problem.

This course is very good at establishing the fundamentals of 'problem analysis' - something which a lot of analysts actually struggle with. I enjoyed it and found the examples helpful to think through the various steps and types of ML applications.

Learned a lot about dealing with datasets where training data and test data might not have the same distribution. In a practical deep learning project, a lot of decisions are strategic and this course will definitely help in making better decisions.

Another great course from Andrew Ng. You will learn how to manage deep learning project and get to know some clever ideas of approaching the project from managerial perspective. You will also get to know important people in deep learning community.

Pretty important course in my opinion. I had skipped this course last year when I was new to deep learning. One year later after working on some deep learning projects, I feel this course makes a lot of sense to me and I wish I had done it before.

I do not think you will find this expert advice elsewhere. And the extended scenarios which the quizzes test give the feeling that I now have real experience (although I do not) making high level decisions about guiding a machine learning project.

An excellent overview of a rarely discussed subject. Often lost amidst the seemingly daily discoveries of new deep learning tricks is need to apply deep learning in real applications. This course did a great job of addressing the latter concern.

One of the key courses in the specialization besides being short and tricky. The content of this course is exactly that which differentiates between a mere programmer from a data scientist or a machine learning engineer. Do not skip this course.

At the very beginning the course seemed to be about self-evident, even trivial things. Now I can't imagine it to be dropped out of the specialization.

Thank you prof. Andrew Ng, you gave us a roadmap to move and saved from many blunders on the way.

A very insightful course detailing the problems encountered in a real-life deep learning pipeline. The solutions were very intuitively explained and the case study approach reinforced the concepts. The heroes interviews too were very interesting.

This course give a lot of insights about approaching a machine learning problem. It doesn't contain a lot of concepts or algorithms regarding ML itself, but the course will be very helpful for anyone interested in working on real life ML systems.

A really must have course for anyone who wants to enter the field of machine learning. The concepts being thought are crucial for creating effective solutions in the modern world. Andrew explains everything in a simple and down to earth approach

This course provides very specific information about best industry practices. When I started it I was ready to underestimate its value, but by the end I realized Andrew Ng provides many insights that one can get only through years of experience.

I think this course is one of the best course which teaches you how can you proceed your machine learning project in various situations and what measures to take while building a ML project. Hats off and thank you Andrew sir. Thank you coursera.

Very helpful to get an understanding of how to structure a machine learning project. Furthermore it is a great guide to get a first intuition on where to spend time or fix errors in a machine learning project and where to go on fast. Great work!

Ce cours donne des clés sur comment améliorer son réseau de neurones et en particulier éviter de perdre son temps à chercher dans la mauvaise direction.

Je n'ai pas encore mis en oeuvre cela, mais je pense que cela sera très utile le temps venu.

Amazing Courses for Deep Learning Specialization, help in making you good with basics needed, and apply the concepts in real-world applications.

Thanks to Andrew Ng for the way he explains every topic so deeply and easily understandable manner.

It's an amazing course for people without ML experience overall. But if you have some experience (deep learning or not), you'll find a lot of basic tricks that you probably already used or figured out intuitively as you worked on some projects.

Knowing just theories won't guarantee one's success in a specific field like deep learning, theory, and experience are both what it takes to be so. This course conveyed not only theory but also many years of great experience from professor Ng.

This is one of the best courses in data science I have ever taken. There are a lot of options out there for taking data science courses, but this one is key to getting organized and know how to proceed with a project what to do at each step.

One of the most helpful 8 to 10 hours of instruction I have ever received in my life. Thanks a lot Andrew, and the entire team for putting this together. I will recommend this course to all my friends and colleagues working in the AI/ML space.

Perhaps the most important course out of the 5 courses, Professor Ng explains really important concepts often overlooked by a lot of machine learning/ deep learning tutorials. This course will really make your good algorithms great.

Cheers! :)

the question on synthetic fog, I would love to know if someone answered to this one right from the first time. It is a designed trap to see if we are just listening to the class and applying or if we really think and work hard on each question

Awesome course. Hats off to Andrew for how this course is organized and presented. The simulator exercises are very good too. I'm yearning for more such exercises. It feels like I gained real-world experience without working at an AI company.