Learner Reviews & Feedback for Structuring Machine Learning Projects by DeepLearning.AI

This course was new for me. I only had some prior knowledge about transfer learnign because I use it on my Bachelor´s Degree Thesis on image segmentation using Imagenet pre-trained weights, but all other concepts and all those guidelines of how to structure a project and how to solve the problems for make a faster and successfull iteration was really helpful

Machine Learning Flight Simulator was an intriguing adventure, you get the feel of being inside the shoes of real life AI project leads! Words can't describe Andrew and team's efforts, brilliant guys! Keep up the good work :). Really excited to see what challenges you've got in store for us in the upcoming Convolutional and Recurrent Neural Networks courses.

This was by far one of the most challenging courses in the deep learning specialization as it covered a lot of practical ml implementation. I personally think that the ideas and the strategies discussed in the course will be highly useful while implementing real-life models. The assignments are very well designed and created a real-life scenario environment

Andrew Ng is amazing. The way he focuses on these very often overlooked details of ML projects alone would qualify him as a professional of a different category. On top of that he has an incredible ability to explain complex things in an easy way. If he was a baseball player he would be hitting 60 HR per season while pitching 40 games with a 0.87 ERA :-)

Thanks a real bunch, Coursera for providing financial aid and bringing up this course, truly loved each and every section, coupled with quiz section at the end, is so much helpful and of course, very thoroughly made! Thanks to all the hardworking instructors and teaching assistance, and of course, coursera team for making this course so effectively! :)

It gives an eye opener for a new learner like myself. This training brings about integrating fractions of my knowledge from my previous Data Industry. If you are new to Data-driven business, I would not recommend you to take this course. You should at least have 2 years of Data-driven business experience to understand the context of the materials.

Generally felt this course is super useful as it helped answering several questions of "why we do things this way" rather than follow the paradigm of "it just magically works". Though there are still many magic moments while learning on ML in general, I felt this course really helped broad my view and understand the overall problem space much better.

Having finished the first three courses in the Deeplearning.ai's specialization, I find this course is the most valuable one. It is not telling you the basic algorithms like the first two courses, but telling you how to ANALYZE you project as a whole in each step, and where to go next. The first two tell you how to build, this one tells how to THINK.

Excellent guide work by Andrew NG,

I really like the way he delivers the intuitions or insights from deep networks. The most important think when working with these kind of project is to look below find what you missed in considering higher level extraction. I'm really inspired by his work and keep the advice to improve performance for all projects.

Maybe its different and should help us not just thinking of Algorithms and models ,we should think out of box and think of the error from different approaches as human relative to the machine, think of the data we have, think of different distribution of the data, trying to knowing with different approaches how we should care about of these error.

This is a very good course. Worth taking. I am currently a data scientist and in my daily work I face a lot of data mismatch problems and I have no idea what to do after error analysis. This provides a very good guideline of how to structure our deep learning projects and what should be the thinking logics behind. Thank you Andrew I really love it.

Have taken a formal 1 year course from a prominent Institute but these kind of concepts were never covered there. The beauty of this course and all courses by Andrew Ng is that they are so simple and easy to understand that one can't help but only understand the concepts. Best methodology and delivery of teaching I have found online. Thanks a lot.

Excellent course and well presented material. I would like to recommend all the ML engineers to review this course before starting actual development. This course explains different intuitions and techniques with reasons what to choose, where to apply and when to apply.

Great course. Enjoyed a lot. Thanks Andrew for your precious time and efforts.

So far the course I found most useful in the deep learning specialization.

Does away with the copy-paste programming tasks, compacts everything into two weeks and gives a lot of valuable insight on the proper mindset to make a machine learning project work.

The flight-simulator quizzes really made you think and reflect on what the lectures taught.

Having followed this course I have learned how to address common problems that I have found in the evaluation of performance of my neural net based on fed datasets. I am now able to reason much better (thoughtful) on the problems that I encounter having learned some error analysis techniques which have been addressed in this course. Thumbs up!

I really liked the programming assignments in the two previous courses (although, it was usually not enough challenging for me). In this course, I found "case study" assignments very useful and exciting. So far, I am very satisfied with the DeepLearning Specialization; I will definitely continue to the 4th and 5th course. Many thanks for it!

The strategies, guidelines, and best practice taught in this course will help students pinpoint the directions accurately when managing a deep learning project, saving enormous time and resources. The "flight-simulation" style assignment is very useful in training students for managing a deep learning project in various real-life scenarios.

I thought it's a trivial course and I didn't expect that much. HOWEVER, I must say this is one of the most important courses EVER in ML. SO MUCH I should larn before doing my dissertation. I really don't need to DIY so many things. Thank you, teacher Andrew for sharing the treasure experience. I really learn many concepts from your lecture!

Wow. This course is densely packed with really great *practical* and well-justified advice, based on Prof. Ng's extensive experience. There's lots of wisdom here for taking the step from understanding 'in principle' how machine learning can be applied, to having practical understanding of the techniques to get it to really work in practice.

Very interesting course to avoid common pitfalls and have already some developed intuition without having worked in any ML project before.

The case studies in the quiz are extremely helpful as some concepts can be a bit confusing and they help clarify the doubts you might have in the subtleties between the different situations you may find.

"Structuring Machine Learning Projects" provide so many good practices in how to correctly implement Deep Learning Models, troubleshoot them and make them better, the tips and recommendations are excellent, highly recommended to anyone interested in deep learning this is a fantastic Course, thanks to everyone that make this Course possible.

When you deiced to join AI teams, you need to tackle out-of-the-blue and state-of-the-art problems. Managing this kind of situations aren't easy and need different tips and tricks based on the problem statements. This course come up with brilliant ideas to make up your mind in these challenges. Great job! Coursera and deeplearning.ai

Thanks

The concepts taught in this course are giving very basic foundations which are essential to build deep learning career. I no longer scared to talk confidently about a model in terms of bias, variance, error etc. Though this course was scheduled for 2 weeks, because of interest that it created, I am able to complete it in a day. Thank you.

This course gives a very intuitive understanding for analysing performance of neural networks and strategies to go about improving them. Also liked the introduction for Transfer Learning. The quiz which was kind of a pilot simulator for machine learning project, is excellent in understanding the decision making process for such use-cases.

Really well structured material! Don't be fooled by the lack of assignments, though; this course is pretty theoretically challenging. Pay extra attention to all the data distribution lectures - they are bound to come in handy in practical use. I learnt tons of really useful information from this course. As usual, hats off to Prof. Andrew!