I have learnt a lot of tricks with numpy and I believe I have a better understanding of what a NN does. Now it does not look like a black box anymore. I look forward to see what's in the next courses!

This course is really great.The lectures are really easy to understand and grasp.The assignment instructions are really helpful and one does not need to know python before hand to complete the course.

Amazing course for anyone wanting to jump in the field of deep learning. Andrew explains the details very well. The assignments were structured very good that provided detailed instructions. Thank you

One of the best courses I have taken so far. The instructor has been very clear and precise throughout the course. The homework section is also designed in such a way that it helps the student learn .

At first, I want to thank the course teacher and all the others for providing us such a wonderful course. The way the professor teaches is really very very helpful. Thank you all again and keep it up.

Too slow, a lot of repeating facts, very little contents in total in the course, and nothing new compared to the old machine learning course which was more fun and much faster. Nice environment with python notebooks though!

It's really quite an amazing course where we get to learn the mathematics behind the Neural Networks. It is great to learn such core basics which will help us further in developing our own algorithms.

This is really a very good introductory course for people from various background. The assignments are also nicely designed to give an insight to how things works.

But at times, in order to make this course appealing to non-math/engineering background, it at times trivializes some important mathematical concepts and notions, in order to not scare away people who are not very comfortable to mathematics.

TL;DR: It's a good course for people who are not familiar with neural nets. Otherwise, it feels kind of repetitive (I completed the course in 4 days)

Pros: Learn to implement efficient feedforward neural networks from scratch, by taking advantage of vectorized operations and caches; good understanding of how neural nets work and the reasons of their success; I loved how Dr. Andrew explained why we must initialize the weights to some small random numbers (I already knew neural nets before this course)

Cons: I expected to build neural nets in Tensorflow (after learning how to implement them from scratch); It'd have been good to include a gradient check (by computing the numerical gradient) to foolproof the backward pass; sometimes the explanations felt kind of repetitive (e.g. continuously going from one training example to the whole training batch). I would have just sticked to the batch learning after it was introduced

If you are already used to Python/numpy and you followed the free Machine Learning course from Ng, you really won't learn anything, apart from a new activation function.

Coding Exercise Were quite simple, a full length assignment would have been better.

Wouldn't recommend because of the very low quality of the assignments, but I don't regret taking them because the content is great. Seriously the quality of deeplearning.ai courses is the lowest I have ever seen! Glitches in videos, wrong assignments (both notebooks and MCQs), and no valuable discussions on the forums. Too bad Prof Ng couldn't get a competent team to curate his content for him. For such an basic level of content, you will find many other courses that are far better.

Too easy

A good mix of theory and practice. The learning curve was perfect for me, and the course schedule is right if you study the material and work through the assignments in your spare time. Assignments are very well structured, I feel that trying to create the same implementations by myself (i.e. without the guides in the assignments and intermediate tests / check) would have taken 10x long.

This is a good review of the concepts. It helped even more once I finished the course and reflected on the material by working out the equations for back propagation by my own hand. Looking forward to the next course in the series.

Excellent course. Challenging, but doable. Andrew Ng is a great teacher. I learned about logistic regression, forward and backward propagation, code vectorization with numpy, activation functions, and many other topics.

The course is good and it helps to clear the basic concepts of Neural Networks,

And the interactive assignments are just Awesome

This course is good to just learn the terms and the basic aspects on architecture of deep learning. There is hardly any big explanations on the mathematical foundations of the topic which are of extreme importance to understand it.

It is a course for someone that dos not know much about neural networks or mathematics.

Is unfortunate that lead researcher in the area is able to say that it is not necesary to understand what a derivative is to be able to understand deep learning and the algorithm to update the weights of the network. I guess only for a first time course that is true, but I was expecting more from this course.

Programming assignment is too simple

Very basic level

not satisfied

I think that this course went a little bit too much into needy greedy details of the math behind deep neural networks, but overall I think that it is a great place to start a journey in deep learning!

Very structured approach to developing a neural network which I believe I can use as foundation for any project regardless its complexity. Thanks professor Andrew Ng and the team for their dedication.

The course is quite slow, but covers the basics of early deep neural networks (NNs). It does seems not to assume any prior knowledge on calculus, which is emphasised extensively, which sometimes leads to more confusion than that it is helpful. Before starting, some knowledge on python, numpy and linear algebra is highly recommended.

In the end you will have a basic understanding of what a NN is all about, and you will have built a photo-classifier. The course however, spends a lot of time explaining simpler concepts, while quickly glossing over the deeper stuff. Because of the elaborate explanation of simpler concepts, the big picture often gets lost. Furthermore, it seems like the videos, quizzes, and programming exercises were made by different people. The quizzes cover things not covered in the videos, and the programming assignments cover things not covered in either.

The course does not have the same quality as the “Machine Learning” course Andrew Ng made with Stanford.


The biggest issue are the programming exercises, that do not require the learner to think at all. Most tasks in them are on the level of “copy and paste this piece of code”, “retrieve a value from a python dictionary” or “use a mathematical formula displayed directly above”. I appreciate the effort to make the course more inclusive to people with a weaker background in Computer Science. It would however make the course much more worthwhile to have challenging exercises with optional hints, instead of giving the solution away in each task description.

“Neural Networks and Deep Learning” hardly teaches anything, that wasn’t already covered my “Machine learning”. The major differences is that it uses Python instead of Octave and arranges features as rows instead of columns. In my eyes, the learners time is better spent, skipping the first course of the Deep Learning specialization entirely and taking the Machine Learning Course instead. To the creators / maintainers of the course I would advise creating a summary, that covers the most fundamental differences between the two courses (different notation, numpy fundamentals) and make a suggestion where someone who has taken Machine Learning should join the Deep Learning specialization.

While the audio quality has improved, the video editing is poor. There are multiple occasions where misspoken content, that was clearly meant to be edited out, remained part of the video. Many videos are preceded by a “Clarification” reading task that corrects some mistake in the video. How hard is it to get an intern to fix this in post?