Andrew Ng is a fantastic intructor. I admire his teaching style. He pays so much attention to the fundamentals instead of rushing through the material, that I feel like I learned something that will actually stay with me. The homework codes are written beautifully. Introduction of broadcasting and vectorization was an eye opener - turns out I've been programming very inefficiently for years without knowing. This course on it's own is not enough for me to go and architect NNs on my own, but it definitely helps with general understanding of the process, I feel more confident now talking about it and reading papers. Will continue on to other courses in Specialization.

A must for anyone in deep learning research. This course aims to build the foundation of deep learning operations by not using the built-in functions but writing code yourself, which help tremendously later. It gives you the microscopic view of what calculations are carried at each neuron, layer, forward pass & backprop.

The interviews provide the right kind of motivation for aspiring researchers. They're like the cherry over the cake! The syllabus describes the course material but whats a plus in this course is Prof. Andrew Ng's tips when it comes to applying techniques and information about the latest (and probably near future) trends of the academia and industry.

After studying Lesson 1, I learned a lot and solved many problems I've been puzzled before. Andrew-NG's depth explanation and detailed writing move me deeply. Teacher's profound knowledge and responsible attitude is my learning example .The teacher can make the complex knowledge lively and interesting, but without losing its own contagion. After-class exercises design is also distinctive, providing great convenience for our beginners . After class, the active discussion and exchange provide a wide range of ideas and rich ways to me. Thank you, deep leaning team. we thank coursera for offering rich courses, thanks to Miss Wu's team for doing so excellent course.

A few months ago, I didn't know anything about machine learning. Machine learning context was a wonderland for me and I decided to dive in. I began with "The Machine Learning course by prof. Andrew Ng.

I thought about how can merge my knowledge of embedded systems with machine learning. I understood that the implementation of deep networks on customized hardware such as System-On-Chip is an open issue.

Now, I learning more about deep learning through DeepLearning.ai courses on Coursera.

I'd like to special thanks to Andrew Ng, Kian Katanforoosh, and Younes Bensouda Mourri for this curriculum.

I wish that finding a position for implementing deep learning on edge.

Considering how clear and thorough lectures by Andrew Ng were and overall how hard things were made simple in this specialization I can't give it anything but 5 stars. Thank you very much for your hard job on it!

However, I would prefer a bit harder and more theoretical course, personally. This one was adapted for a very broad range of listeners, which is a good thing generally. But it is absolutely not challenging to pass it: for instance, the programming excersices are great notebooks, but they mostly are already solved for you and you only need to fill the right lines into the right places. Only the last course on sequential models probably was a bit harder.

If one has already completed Andrew N.G.'s Machine Learning course that works on Octave & Matlab, then this course will be a piece of cake. However, the refresher here, is Python! And there are SO MANY things that course expects you to know - so much to learn! The Material is designed to NOT MAKE YOU UNCOMFORTABLE but if you really want to Learn Python, then you will have to take it as a challenge and learn pretty much everything that you see as unknown there.

Overall though, really excellent course material. Glad I picked up this course. And I think it is a good revision for one already versed with ML concepts that one can easily pick up this Specialization.

Very well designed and thought through course - Highly recommended for those who want to learn neural networks from scratch even extending it to deep learning.

This course will empower you to understand, create, and tune a neural network. Clearly describes about Parameters, Hyper-parameters tuning, Forward Propagation, Activation Functions, Backward Propagation, Updating Parameters and Predicting Labels.

On a side note :: Before this course I was only aware about analogy of human brain's neurons and neural network and after this course I am able to understand that no one knows (even neuro scientists) that what a single brain neuron does.

HaPpY Learning Guys !

Good introduction to Neural Networks. Professor Ing does a great job of simplifying the ideas for folks like me who did Masters in Operations Research more than 2 decades ago. This course brought back the happiest memories of my graduate school days on how gradient descent works. The course also took away the mystery I felt about what I am familiar with i.e. optimization vs how the human mind works. I have not gotten a clue on how the human mind works. I have no idea on how the neurons in the brain fire. I just know that neurons form a giant network and I have always enjoyed network flow algorithms thanks to Professor Dijkstra. This is a really good course.

An excellent introduction to neural networks! Andrew Ng is an engaging communicator, and the course offers programming assignments that give you an opportunity to apply what you've learned immediately. The programming assignments are, however, somewhat remedial. My only wish for the course was that the programming assignments were a little more extensive to really test your knowledge of the backpropagation algorithm, but I also appreciate that would lead to a much lower success rate for students, and is also something students can work on on their own time. Overall, this is a great introductory course with good fundamentals in the concepts of deeplearning.

Excellent introduction to neural networks and deep learning! The course is very well structured, coming from the basic concepts of neural networks, up to building a modular deep layered network. Andrew does an amazing job at concentrating in the underlying and most important principles of deep learning, without spending too much time into the nitty-gritty mathematical and technical aspects of the topic. The lab programming exercises are insanely well written, and the ML interviews at the end of each week gave me a lot of perspective into the field and motivation to keep learning. Thanks to the deeplearning.ai team, you made an amazing job with this course!

Fantastic course, even better than the ML course by Andrew Ng. I love the Jupyter notebooks and have found them such an improvement over the ML's (already good) approach with MatLab. I've learnt tons not just from the course content, but basically from dissecting in my own Jupyter notebook what is going on in each lecture and programming assignment.

This course/specialisation is worth every penny. The interviews with heroes of DL have been very interesting and add a lot of value too. I love that Andrew always asks them about career advice and found Ian Goodfellow's interview particularly inspiring. Thank you Andrew and to all the team making this possible!

This course is excellent for both total beginners and people with a little experience in deep learning. I've implemented a few DL networks before, setting hyperparameters based on best practices. However, in taking this course, I came to understand the reasons behind some of the best practices I've used in the past. Dr. Ng does a great job of training and scaffolding for each lesson, building on the previous materials and leading to the next lessons. I'm also glad that he included interviews with big names in Deep Learning, so that I could see what's going on in the cutting edge of DL research, as well as finding more resources for learning even more.

In general it could be more condensed. Instead of too many repetitions of the fundamentals I would have appreciated to get an overview in the first course on how CNNs, GANs and RNNs works roughly and when to use it. With this basic course. So I did not gain an overview in order to decide whether I need another course or if the basic deep networks are sufficient for my use case. I missed the part "what kinds of NNs are available on the market for what purpose".

In general the course was too simple, since I already know both linear algebra and Python very well. But this is of course no weakness of the course. I still learned a lot and it was worth doing it.

I found that the course was perfect and gave me a very top level overview of the ML. As a computational scientist I have considerable experience in the linear algebra, I did find that some classes were overkill since they focussed more on dimensional analysis and getting matrix dimensions right, something that (I consider) should be a requirement for this course. However, I do understand that the course is not created only for me. I was really happy to receive a "big picture" understanding of the subject, the teaching was simple and patient. The coding exercises were perfect for a first course in this subject. I can't wait to explore this field further.

I had previously gone through the popular course on Machine learning by Andrew and that course was quite exhaustive for starters. In this course we learn about how to build deep networks through python programming language. My one complaint is that the programming exercises were easy compared to his previous course. I think starters also wont find the programming exercises very difficult.I found the python implementations very good. The way you build helper functions first and then go on to program higher Layer neural nets. Through this course you will learn not only the basics of deep learning but also how to structure your code in an efficient manner.

Really a nice course to take. I´m deeply thanked to Andrew because of his large capacity to simplify complexity - he's really didactic. I loved the way he build concepts from the very simple to the most complex, so that one thinks -- got it!. I like the interplay Adnrew uses between building blocks conceptualization (practical) and algebra & analysis foundations beyond (theoretical background). The assignments are very practical to follow , though after the course one probably couldn´t code from scratch unless she has a large practice on Python, the course is enough to settle the main concepts and learn a good collection of nice tricks in Python.

Well , this has to be the best course for intro to Neural Networks and Deep learning . This course dealt with the basics and mathematics behind Neural Networks and the coding part was well covered in the assignments . If you pay proper attention during the lecture and make notes (I wrote in notebook) , it will help you later while revising all the concepts .

And while doing the assignment be honest and if you're not able to get any answer , just think for some time , pay attention to the small mistake you may have done , revise the concepts and you'll definitely get the answer .

Thanks and Congrats Andrew and his team for making such a great course

Great foundations. I really like to learn from the bottom up and this class provides exactly that experience - build your own NN from scratch. While I do like using Jupyter notebooks for the class to avoid the need to configure a local dev environment, I also find the "write 2 lines of code" style a bit limiting. At times (especially on the final assignment) it felt like it was more an exercise in book-keeping than exercising my knowledge. But of course, for a robo-graded class I think it would be a lot to expect more free-form assignments.

This is a great first class on deep learning and I will highly recommend it to my colleagues at Microsoft.

I was implementing convnet using keras for my undergraduate thesis before, and confused with the terminology used (hyperparameter tuning, gradient descent, global minima, etc). Alas, i persevere and finished my thesis with explanations i found online (albeit with much-unanswered questions and uneasy feelings). I decided to take this course to really dig deep into how this so called "brain simulation" works and i'm glad i did. It's giving me the much-needed intuition into how neural network really works. I now understand the mechanism behind gradient descent, and even gained insight into what derivatives really is (it is just a rate of change!)

The course was great. The videos provided very clear explanation and intuitions behind critical components of the Neural Network. The course built beautifully from a single neuron to a multi-layer multi-neuron model, making it clear step by step. The most helpful & interesting part of this course were the quiz and assignments. Assignments gave a great understanding on the implementation of neural network and how to build them in a very modular way. Building this way, will really help anyone define and experiment with different models easily. The sincerely appreciate the time invested by the authors to build this quality course. Thanks a lot.

This is a nice follow-up to Andrew Ng's Stanford ML course. This one digs deeper into neural networks specifically, so if that's what you're interested in, this is a great course to take.

Note that the Stanford course used Octave and this course uses Python and NumPy (in Jupyter notebooks), so this is also nice because it gets you accustomed to using technologies that are more similar to what real ML practitioners are using. This course does still have you implement things by hand with NumPy and does not delve into higher-level frameworks like TensorFlow. For that, you will have to wait for the next course in the Deep Learning Specialization.

This course gave me an excellent overview of Neural Network, from the metaphor idea to math and implementation in Python. At least for me, the best way to study was a mix of pencil & paper (test and prove all equations) and reproduce the codes in the Coursera platform and Google Colab. The practice assignments are very related to theory lessons (equations using the same notation) that help the understanding. Only one note about the issues in notebooks, the Numpy version adopted is not the most recent, thus it is necessary to change some little things in order to reproduce the practice assignments on Google Colab (but this is not a problem).

This course is amazingly paced and also strikes a very good balance between required knowledge and depth of the topics covered. I cannot imagine how to improve this course except by asking for "more of the same". I had enough background in math and computer programming and I read already some articles and tutorials on Neural Networks. But only after this course I grasped the concept a little better. Andrew Ng is a very good educator: always ready to trade one pound of mathematical rigor for an ounce of intution. And I believe this is the only way to provide good contents here on Coursera. I strongly encourage everyone to take this course.

An excellent course to dive theoretically into basics of deep learning and also develop good intuitions about neural networks. Intricate details of linear algebra and the mathematical equations involved are neatly presented throughout the course. The programming assignments are meticulously developed to provide a very comfortable interface cum understanding of the problem, enabling the course learner to implement deep learning models on interesting set of classification problems. Adding couple more such problems (where one would use the already developed models) can make the practical learning experience even better. Enjoyed the course!

Very practical approach, full of code examples. It teaches you how to implement the NN with multiple layers from scratch in incremental steps. From the easiest approach (with single layer) to multiple layers. The code uses mainly simple code structures (i.e. loops, dictionaries, lists, vectorized operations and functions), so you do not need knowledge in OOP. Although I think some concepts if explained in OOP framework would be easier to grasp. But this is my subjective opinion. The course material is very well explained. If you want to learn and understand the way neural networks from inside out this course is definitely worth taking.