the tips are given by Andrew Ng...that is the best for any machine learning project... I think everyone should try this course for performing better on the ML projects...once again thank u Andrew for this such a good content...highly recommended for everyone.

This course has given me a systematic insight of machine learning project, which helps me to handle the machine learning problem from a global point of view. I'm eager to apply these knowledge in real machine learning project to better understand the essence.

A very much essential course for a ML team manager.. In-depth insights into the error analysis and to study the performance of the network in different perspectives. Hats-off to Prof.Andrew Ng for very nice demonstrations with lots of examples and case study.

Worth the time and effort. Although this course did not contain the programming aspects, but it was helpful nevertheless. This course actually taught me how to properly go about my machine learning project and how to troubleshoot if I encounter some problems.

This course give me direction to structure my project in better way. Content of this course was really awesome and most amazing part was the flight simulator for machine learning. Thank you Andrew Ng sir for beautifully presenting the idea, thank you so much.

Short course but i think this is the most important course out of the 3 as it is more applied. Everything in this course is new to me... , had to read the discussion for help on the quiz. Hope to appreciate what i learn after i start my deep learning project!

Knowing the algorithms alone doesn't help much in developing ML applications. We should be able to tackle any problem and drive our project towards the intended goal.This course provides some handy tips and tactics for the same.Well taught as usual. Cheers!!!

This course is very useful. The 'Simulator' is very cool. After finishing the homework, I have a better understanding on how do deal with a real project. I'm trying to solve a problem in my work, I think this skills mentioned in the course will help me a lot.

This course was directed towards giving more of a general perspective on an ML project. Although it was a brief one, it gives enough insight to continue and develop on the concepts taught. The best part as always is the inspiring and motivational guest talk.

Un curso corto con mucha información, pero muy muy instrucivo de cómo abordar los proyectos de deep learning o redes neuronales, se te enseña desde el análisis del error hasta la transferencia de conocimiento, lo cual es bastante interesante.

Muchas gracias!!

It's really nice to have Andrew share his practical knowledge and experience. Paying careful attention to data distributions and doing ErrorAnalysis to learn where to focus your efforts are valuable insights. Thanks for making us all better DL practitioners.

This course gives you a good understanding of how to approach deep learning projects and machine learning problems in general. After this course you should feel more comfortable understanding how to structure your projects and better optimize your time use.

Andrew provided lots of information in a two-week period due to this the course feels more dense than the previous two. The quiz has also been more challenging. Overall though, it is still top notch teaching from the best. Looking forward to Course 4 and 5.

Prof.Nag and Team, had really gave immense effort to make things brain friendly. Really appreciate the effort to make this so easy going, but conceptually very high content. Recommend not to finish over night, but trick is to go slow and grasp the content.

This course is very important as it offers solutions that don't exist in literature to tackle real DL problems. Andrew Ng is basically teaching you from his vast experience. I highly recommend it esp. for those who want to design / implement DL products.

Outstanding course with immense amount of real-world cases from industry. However, there is no programming tasks here in this course and I was feeling a lack of programming assignments a bit. But overall, the theory and case studies are just incredible.

I think despite being more theoretical course than the previous ones, it is still one of the most important courses in this specialization as we learn about how to handle a real life project and mitigate the problems that arise in a more systematic way.

The content is super useful. I have struggled in my previous projects with many problems discussed in this course. It is great to hear Andrew Ng's opinion and his suggestions will definitely help me push the next project better into the right direction.

I think this course covers the cases where I tend to bog down and waste time, and has provided me with useful and practical guidelines to get out of them. You should not underestimate the value of this course,

just because there is no coding assignment.

In this course, the instructor shared various methods to point us in the right direction of where we should improve our model. Also, many new techniques were also discussed in this course which help develop accurate model even with fairly little data.

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.

Excellent overview of common pitfalls and problems you might encounter in a machine learning project. The lectures use good practical examples to highlight the issues. I definitely gained a better understanding of how to set up and run an ML project.

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.