If you want to break into cutting-edge AI, this course will help you do so. Deep learning engineers are highly sought after, and mastering deep learning will give you numerous new career opportunities. Deep learning is also a new "superpower" that will let you build AI systems that just weren't possible a few years ago.
In this course, you will learn the foundations of deep learning. When you finish this class, you will:
- Understand the major technology trends driving Deep Learning
- Be able to build, train and apply fully connected deep neural networks
- Know how to implement efficient (vectorized) neural networks
- Understand the key parameters in a neural network's architecture
This course also teaches you how Deep Learning actually works, rather than presenting only a cursory or surface-level description. So after completing it, you will be able to apply deep learning to a your own applications. If you are looking for a job in AI, after this course you will also be able to answer basic interview questions.
This is the first course of the Deep Learning Specialization....

Jun 30, 2018

Very good course to start Deep learning. But you need to have the basic idea first. I would suggest to do the Stanford Andrew Ng Machine Learning course first and then take this specialization courses

Dec 04, 2018

Extremely helpful review of the basics, rooted in mathematics, but not overly cumbersome. Very clear, and example coding exercises greatly improved my understanding of the importance of vectorization.

筛选依据：

创建者 Aaron H

•Sep 01, 2017

Good coverage of the basics of neural networks with hands-on exercises using numpy.

The notation is a little surprising -- most of the time we math people talk about dy/dx as being the derivative of y with respect to x. That is, when I wiggle x a little, what happens to y? The notation in this course assumes that everything is a derivative of the cost function with respect so something else, so the notation only includes the "something else". For example dW is the derivative of the cost function with respect the weights in the matrix W.

If you are not careful, it is easy to lose track of what dZ means.

If you are pretty comfortable with vector calculus, it moves pretty slowly at times. If your calculus is rusty, I think the speed is probably perfect.

创建者 Jeff W

•Oct 08, 2017

While I'm good at perl, I wanted to learn python, and as I'm a learn-by-doing kind of person, I thought an ML course in Python would be a good place to start. I was surprised that "Deep Learning" was a bunch of the neural network techniques I'd played with in the past, and was a bit apprehensive about the amount of calculus that would be required.

This class breaks down the ML concepts quite simply, and helps you understand how to actually build and apply logistic regression, and then use that as a building block to deeper neural networks. They also give you an intuitive understanding of the mechanism and underlying math, without requiring endless pages of derivations.

I recommend this course to anyone looking to get a solid overview of ML techniques.

创建者 Shehryar M K K

•Oct 02, 2017

This was my first foray into the field of deep learning. Dr. Andrew is an amazing instructor his humble demeanor made learning really enjoyable. I really like where he went into derivatives and did it step-by-step making me understand the math behind the scenes. The programming assignments were super easy only difficulty was my lack of practice with python. If I would have to improve on this course. I would say add articles for further readings with a short quiz after it related to the article. I would also like to take this opportunity to thank the coursera team who accepted my application for financial aid without which I would have never earned this certificate. Thank you for allowing me to learn something new and for making it easy and enjoyable.

创建者 Tyler K

•Aug 19, 2017

Fantastic as always. I do wish it had a lot more math but I understand the challenge delivering that to a larger audience. My favourite aspect of Andrew Ng's classes is actually the absolute response by the grader system.

I learn very effectively in environments where I receive complete feedback on my problem submissions. Allowing me to correct my understanding of the material and retry. Contrast this with the PGM course where total scores are not returned and there are a limited number of submissions. I felt that my learning was stunted in that environment as there was no opportunity for me to correct my understanding of the material myself and have it re-scored.

Hopefully we'll see more math heavy classes in the future that retain this style :)

创建者 Arpit S

•Dec 09, 2018

Finally, I had to sit down at a stretch and finish the course at a go! I think it was completely worth it and I thank coursera team for providing me financial aid to take this course. I am very grateful to have got this opportunity to learn from this excellent course. Will definitely complete all courses within the deep learning specialisation by a little at-a-stretch effort and i am sure it'll give a sweet boost to my understanding. The course material, Professor Andrew's way of explaining and the assignments are all incredible and i really enjoyed the modules for implementing back-prop the from-the-scratch way! Personally, I also feel the best way to take these courses is at a stretch which completely connects the dots for me. Thank you team :)

创建者 Bryan H

•May 28, 2018

The programming assignments give you the hands-on experience you need to feel comfortable coding your own ANNs from scratch. Andrew's lectures are well-paced, easy to follow, and enjoyable.

Room for improvement:

The Jupyter notebooks, although convenient for the Python programming assignments, are unreliable. I spent 25 % of my time re-writing code because the notebooks wouldn't save, and I had to reload certain assignments multiple times, often at different times throughout the day. If you have made progress and the page doesn't save, then leave the tab open and copy-past your code into a new instance. Nonetheless, I can't fault the Instructors for the lack of fidelity in the intercommunication between Coursera's platform and Jupyter's notebooks.

创建者 Liaw S W

•Sep 17, 2017

It was a great course, very well organized but after doing the programming assignments, I feel that I might not have fully grasped the concepts in lectures. The descriptions in the assignments were great and helpful, but I feel that the pace of the course was too quick, too easy. I feel that I must be missing out on something. Maybe it's because the teacher has done a very good job in explaining hard to understand concepts to the degree that they seem too easy to understand. Since this is only an introductory course in the series, it is understandable that it is supposed to be easier. Don't get me wrong, this course has very much substantial contents to it! Nonetheless, it was a great foundation course for the specialization! Thank you teacher!

创建者 Noelle M V

•Aug 29, 2017

If you took Andrew Ng's original Machine Learning Coursera course in 2012 (as I did), you expect nothing less than an excellent course. Unlike Neural Network or Machine Learning courses at other learning sites, this one is far superior. If you are to ever going to fundamentally understand what is going on inside all those convenient Machine Learning and Neural Network software libraries and frameworks (versus just blindly using them), or perhaps build your own libraries; then you need this course. And, indeed, it is important to understand because not understanding removes all intuition as well as removes knowledge of boundary and limiting cases that you may encounter, which will make things harder for you. I highly recommend this course.

创建者 Keely W

•Mar 12, 2018

I'm LOVING these classes!! The instructor, Andrew, is excellent, and the material is presented in a logical progression so that it's not too overwhelming. It definitely helps to have some background in math, namely Calculus and Linear Algebra. The programming assignments can be a bit tough if you don't truly understanding which Linear Algebra methods to use, i.e. dot product multiplication vs element-wise multiplication, but usually the instructions are good. However, I found myself having to look up a lot of Python and Linear Algebra basics online (Stack Overflow is your friend in this case.)

Definitely a challenging set of courses in the Deep Learning Specialization, but very well presented, and extremely interesting (at least to me.)

创建者 Gary N

•Feb 29, 2020

This course allows you to quickly catch up to the fundamentals of building multi-layer NN models, by viewing it as stacks and layers of logistic regression units. You will sail through this course if you already know logistic regression. Even though nowadays most people don't even need to understand how the calculus actually works beyond a basic intuition, the calculus required for back propagation are well explained; detailed yet presented well for people with high school calculus to understand. The exercises are very simple with an objective not to test your ability to write code, but your understanding of how the steps are put together. The answers are practically given to you, you just have to put them together in the right way.

创建者 Akhil C V

•Aug 09, 2018

This course is phenomenal. Even as someone who's spent almost a year working as a deep learning engineer, there were still many lectures I found incredibly useful. I believe the matrix dimension lecture will permanently change the way I structure the code for my neural networks in the future. If I had one criticism it'd be that it could perhaps get progressively harder. I love the ultimate task (of a logistic classifier), but as we go from week to week, I think there could have been less hints. Even by the end of the course, I felt like I was being spoon fed through the programming assignments. This is a problem, because I'm less confident than I would have been if I'd figured out the Lmodel forward propagation (for example) myself.

创建者 Irfan A M

•Apr 24, 2020

Learning from Prof. Andrew Ng (Stanford University, founder of Coursera, an eminent researcher in the field of Machine, Deep Learning & AI & founder of so many lead companies in AI) indeed Blessing.

Such a composed course you get a chance to learn the underlying concepts of AI, Machine & Deep Learning, and implement real-world problems to get intuition and exposure. The design of course content and relevant assignments develop your concepts deeper and intuitive.

One of the prominent features of this course was listening to Heroes of Machine, Deep Learning & AI; Prof. Geoffrey Hinton, Prof. Pieter Abbeel & Prof. Ian Goodfellow really give you motivation and intuition about latest happenings and future directions these fields.

创建者 Branislav N

•Apr 12, 2020

This is an amazing course. As someone who is a beginner in neural networks and AI in general, I really enjoyed this course. The main plus of this course is that it offers straightforward hands-on programming exercises in Python with very clear instructions and meaningful sub-exercise. The fact that the course is implemented in Python is a huge plus, even for beginners in Python programming. This course enables you to experiment with your own data, after you have learned how to build a deep neural network. Indeed, I did not expect to build confidence that quickly and have own ideas about deep learning projects, after this course. This was a pleasant surprise and I will definitely continue going through the whole specialization.

创建者 Gokula K R

•Oct 19, 2019

Well, the concepts were crystal clear. To be honest, I got them theoretically but when i began coding, I could see that I could not connect few pieces here and there as there was the template given and I just had to fill in the blanks with whatever is given at the beginning of the module. I would suggest to let the learners code few functions from scratch, so that we could know what parameters to input, and what to return in the end. Also I think suggesting learners to visit documentations of few important modules like numpy, pandas, matplotlib etc. and instruct the learners to import them by themselves than importing them straight away at the beginning. Hope this would inculcate the developer culture and practice to beginners

创建者 Anton V

•May 31, 2018

This is a great introductory course to deep learning and neural networks in general. The lectures are brilliant and so are the assignments. Best experience I've had with an online course. This one actually makes you want to complete it. I had some Python experience and a very foggy idea of how neural networks work after watching some youtube videos, however this course gives some really nice foundation for future development in the area. The assignments are easy to follow and give you code to use with things to fill in based on your understanding. This is a good way to get you started, I can now use those ideas to play around with a personal project and learn more. Looking forward to the rest of the courses in the series.

创建者 Diego V R

•Aug 26, 2018

After Prof. Ng's Machine Learning Course, this new course appears at our Coursera's dashboard. I, again, enjoyed listening to Andrew's lectures. My personal recommendation is to first tackle Stanford's ML course and then this one. However, if you can only pick one and you are doubting between Stanford's Machine Learning Course and this one, pick this one, since it covers neural networks with way more detail than the original one. However, take into account that other machine learning related topics do not appear here such as dimensionality reduction techniques like PCA. Amazing treasure to the Deep Learning beginners out there. Thank you Prof. Ng and every one else who made this possible (The whole deeplearning.ai team).

创建者 Nicholas B

•Sep 03, 2017

Definitely one of the best online classes I've taken. Even having studied this material a little bit before hand, I learned a lot--mainly in ways of building an intuition of why certain functions are chosen, or work the way they do. In this respect, I think there are few better at getting to the core of teaching: simple is better.

I appreciate that the course is designed to widen the reach of deep learning, but for those perhaps either more mathematically inclined or just extra curious, I highly recommend Lazy Programmer's Data Science: Deep Learning in Python class on Udemy for only $10. Gives a little more mathematical rigor...and hey extra practice in coding up a basic NN all in one script doesn't hurt. Thumbs up Ng!

创建者 Vivek R

•Aug 25, 2017

Excellent course for beginners who are ready to put in extra effort to understand the material. By extra effort I mean repeatedly viewing the lecture videos and persisting with the programming assignment until the techniques are clear. That said, I am personally slightly disappointed with this course. Having completed Andrew Ng's original 2012 Machine learning course, I don't think there is anything new here for users like me. However it served as a good refresher. The other complaint I have is that the programming assignments are too simple. It's basically paint by numbers. If you really want to understand the material, you should write the programs from scratch and use any of the data sets available on the internet.

创建者 Abhimanyu A

•Mar 03, 2018

What a marvellous roller coster ride it was! Thank you so much Andrew Sir and the entire team for putting up these efforts to provide such high quality material accessible to everyone! Cheers to all of you! I wish one day I would be able to share my knowledge like this! I wish!

One thing that I would like to add/suggest that, please provide some reference links, book recommendations and other useful information in the end of the program for anyone who wants to do some more research on the roots of the algorithms. Doing this, it will continue the learning path for the student and would keep the fire burning in him/her.

Please let me know if you have any questions regarding this review.

Thank you once again. :)

You rock!

创建者 José A V M

•Sep 26, 2017

Amazing!! I've took part of the Udacity Deep Learning Nanodegree, but the math there was just not enough to my taste, here the thing is different, I love all the notation and the math behind. Also there are more focus in build the model step-by-step. As recommendation, I would like to include an activity to sketch the functions of the deep learning layers. For example, if I would like to build from scratch a deep learning model, what will be the functions I will need (in the assignments I could deduce them, but I would have like to have an activity related to this). Also I would like to have a little more focus in visualizing a small neural network, and write the values from the matrix to the visual representation.

创建者 Pradeep K P

•Nov 20, 2017

Excellent course by Andrew and team. I am a big fan of andrew teaching style (since I took his ML course), no fancy screens just basic slides with great contents and explanation. My personal fav part in this course is programming assignment, this part is made very thoughtfully I think there are always some clue in the instructions and comments which one can pick to develop code to solve assignments.

For anyone planning to take this course I would suggest to refresh maths mainly topics like calculus, Linear algrbra, though Andrew explains required maths with a great ease. but still good to have maths background.

I am excited and looking forward to explore upcoming courses in deep learning series.

All the best!

创建者 Paolo A

•Mar 12, 2020

As Business Executive I was rather skeptic and a little worried starting this adventure "in deep" as I have not programmed for many years, but still have some notions of linear algebra for luck. My personal objective is to understand AI deep networks to propagate it inside my Firm and especially to improve quality of living, freedom, sustainability in society. I think I got the right direction!

I have been very impressed by Andrew's approach and style that make you comfortable learning these not simple matters. I wish I could have time to continue the Deep learning Specialization.

Thank you very much to Andrew , to the whole Faculty Team and to the brilliant colleagues attending this wonderful course.

Cheers:)

创建者 Syed M I

•Aug 23, 2019

Mr Andrew will make you climb the mountain while holding your hand.

There were sections in which I found the subject getting a better of me, but at the end of those videos he would come up and say "Don't worry if you didn't get full sense of what's going on" or "This is one of the hardest mathematical portion in machine learning" or "Even after all these years i am sometimes not confident of my approach but the model works magically".

In the confusing sections, he almost writes down the code for you to copy-paste. He had pre-written most of the codes for us, but make us feel that we are the ones writing it, because the ultimate aim is to learn things and be confident enough to replicate the learned skills later.

创建者 Mukesh K

•Jan 22, 2019

First of all, thanks for offering the course on the platform. Before starting the course I had a good knowledge of machine learning and have been thinking about exploring the field of Neural Networks and Deep Learning. I could not do it in my college but the course provided me the opportunity.

The course material is very concise. Professor Andrew Ng presented very complex concepts in very easy language. The Programming Assignments are very helpful. They test and enhance both your Python Programming Skills and python code Implementation skills. While doing the Programming Assignments I was not only learning the concepts but also enjoying them. The entire course as well as the assignments are very much engaging.

创建者 Kevin

•Oct 06, 2017

Andrew you did it again! This is the best intro theory and implementation course on Neural Networks out there. It combines enough theory (optional Calculus/Linear Algebra) and full implementation. The discussion groups are great for hints when you get stuck. Thank you to all the assistants and TA's who put in so much time to this course!

Now, for anyone who is debating taking this, having a calculus and linear algebra background will definitely help you in this course for the theory, but it's not a necessity at all. Some prior Python experience is needed as you will need to understand how functions are being called, but that wouldn't take a lot of time to get caught up on, but would require additional effort.