I like the pace of the course: not too fast, not too slow. Professor Andrew Ng repeats the most important topics each week so it helps to remember things better. The programming assignments are relatively easy--you can reuse the functions you created in the previous week. But even with these relatively easy assignments, you create your own real neural network from scratch! Looking forward to starting the next course!

Incredibly well thought out introductory course to artificial neural networks. Particularly appreciated the intent to have the student build every function relevant for the construction of the neural network architecture on his/her own. The final assignment is extremely instructive and I am sure I will review it multiple times in the future, as it is a great way to dissect the principal steps in forward and backprop.

One of the best course to start learning Neural network.It is a big confidence booster as after going through the course you get aware how a neural network works mathematically and get comfortable building it from scratch.The assignments are well designed and you feel motivated to attempt it and the learning from the course become clearer after attempting these.Must take course for people interested in deep learning.

After having done Machine Learning (Andrew Ng) I registered for the specialization courses of Deep Learning. Key words for this course: practical, to-the-point, good sense what is a neural network and how it works. I liked (Python) Notebook: excellent tool. I watch Andrews online video lecture while commuting to work. Now I can also do the assignment on my way to office.

Can't wait to start with the second course! :-)

Even though I already had some knowledge about Neural Networks, by reading and learning from independent content on Youtube and Google and from reading Scientific Articles, this course was really helpful to me! The videos were not too long and very entertaining, what made the flow of the realization of the course very good. And the coding tasks were not too hard, which made than funny and awesome to make. Thank you!

Great intro course for the Deep Learning Specialization, covering the essential building blocks of a deep neural network, their purpose and the bigger picture. The assignments are indeed helpful in applying the learnings, working on only the parts that are the focus of the assignment, enabling a faster learning. Additional insights from interviews with experienced practitioners and valuable and also an inspiration.

I took a course in NN ten years ago. This course helped me remember key concepts, and taught me new ways to implement an L-layer NN (i.e. using Python and numpy). The lectures are very helpful, and the programming assignments are straight to the point.

One small comment: In the programming assignments of week 4, it would have been better to ask the students to implement the activation functions and their derivatives.

Cutting-edge technologies explained in a very straightforward, yet rigorous manner.

You definitely want to walk through the building blocks of deep learning with Professor Ng's course guiding you there step-by-step, all the necessary explanations always at hand along the way.

You feel that you are pushed to learn and think, but never lost in terms you cannot comprehend.

Thank you for this course and the inspiration!

Ever Since I heard about Machine Learning, I always wanted to build any model from scratch. And this course does not only makes you do it but it also helps you in building your first image classifier and that too from scratch. Really, such a great feeling it is. Thank you so much, Sir Andrew Ng. I will surely meet you one day and will thank you personally for making such a helpful course and the Coursera, of course.

Awesome experience i had while doing this Neural Networks and Deep Learning. Hats off to Andrew NG and his team for the wonderful design of course with graded programming assignment. Teaching Deep learning is very difficult which involves multiple parameters to learn and remember, that up to graded programming assignment is having deep complexity. I strongly recommend this course to first time learners of ANN and DL

Before this course, I was scared to approach ML concepts and tried avoiding the math altogether. Andrew explains the details in depth just to revise or clear concepts, glad I came across this course but I should have completed it ages ago. with a little bit extra resources to refer, you can master the understanding to get a solid foundation in these concepts for further exploring though kaggle or any other platform.

Amazing as always. I find the notation very clear, and I appreciate the effort and the clarity in diagrams and helper functions. It would be really nice to have a video on how you worked through a test case on those small unit tests. The results for these do not seem instant to obtain and perhaps many people just would omit them in practice, while they are of vital importance to get something like this working good.

One of the best courses out there to get you on a solid ground for the math and technology. Some of the exercises and quizzes have problems. Some issues include asking graded questions on material that does not appear till the next section and lab exercises that require information not covered in the lectures or depend on author's knowledge unknown to students. Some of the graded exercises don't accurately score.

First of all I would like to say that this is a wonderful course for the beginners who often wonder how to start and enter into the world of artificial intelligence. This course can be taken to build strong foundation and once foundation is strong, one can further look to dive down into the complex world of artificial inteliigence. Also, I would like to say Thanks to Coursera for providing me with the fee waive off.

Great course! Andrew did a good job in explaining the different systems of neural networks and the way they could be implemented in your own environment. In the videos he did explain everything step by step, so you could slowly getting deeper in all the math and layered networks. The different assignments were the best way to see the results of implementing an neural network. I'm looking forward to the next course.

Gets a lot of the main ideas across well. The coding is pretty structured, and follows the description pretty closely, which makes it a less challenging exercise. But the short functions, and frequent tests, do help build confidence that what you're writing is, in fact, working. That said, in the final notebook, when I uploaded my picture, it classified me as a cat. Presumably I need to take the next course now :)

This course will assist you if you are new to neural networks and wish to learn the fundamental concepts. This course is very well-designed and will help you understand the major technological advancements that are driving the emergence of deep learning. This course's assignments are arranged in such a way that you gain a thorough understanding of how to build, train, and apply fully connected deep neural networks.

Easy to follow and super useful. Clearly Andrew Ng has spent a great deal of time preparing this course. Some of you may have also completed his other course "Machine Learning" at Stanford University - this course is very similar, but slightly more elaborate. In addition (and this is of course a matter of taste), I find the Jupyter Notebook/Python environment much more convenient than the Octave/Matlab environment.

The lectures are thorough and concepts are introduced in a step-by-step way that aid in clarity. This course takes a lot of time, so I suggest that you don't take others at the same time if you are also working, etc. I made the mistake of starting a new job, taking this course and an astronomy course at the same time, and it's a lot. That said, definitely worth it and I'm excited for the rest of the specialization.

For the enthusiasts of Machine Learning and Deep Learning who want to jump in this journey, this specialization is great and almost covers all the topics of the day. The course material and contents are well organized and well prepared. And in spite of natural complexity of Deep Learning, the course is being taught very comprehensible. Special thanks to Andrew Ng and his team for preparing this outstanding course.

I have learnt much. the calculations for back prop gradient descent L-layer neural network was pretty intense. will need time to really digest all of this. It got really mind boggling at some point in time.

I'm second guessing all these functions and calculations of forward prop and back prop are built into tensorflow for ease of use. Just makes it look like tensorflow is a walk in a park and taken for granted.

Through this course, I have a good understanding of the building blocks of a deep neural network and I have learnt how to assemble one from scratch myself. This course did a great job de-mystifying deep neural network, which is really built on the basic concepts of machine learning, like gradient descent. I recommend this course to anyone with basic machine learning knowledge and a familiarity with Python (numpy).

Best introductory ML course on the Internet!

Students of this course will find it extremely useful to go through the Calculus and Linear Algebra courses at ocw.mit.edu to gain a deeper understanding of ML.

Students of this course will also find it greatly enlightening to derive all the formulas presented in this course without proof for themselves using their knowledge of Multivariable Calculus and Linear Algebra.

Very thorough and suitable for people who are interested in learning neural network and its implementation in Python. I particularly enjoyed the clear explanation and emphasis on the algebra behind the forward and backward propagation algorithms. Excited to start my next course in the specialization!

However, I think I would definitely learn more if the programming assignments' instructions were less comprehensive.

Just one word "Awesome". Sir Andrew Ng is an amazing teacher, he simplifies the concept so brilliantly that one can understand easily.Just one little request , can u please make a course on all the other libraries used ,for example matplotlib,scipy,sclearn etc, because though i completed the course , i don't feel satisfied as I will not be able to implement this for my work due to no knowledge of those libraries.