In the first course of the Deep Learning Specialization, you will study the foundational concept of neural networks and deep learning.
By the end, you will be familiar with the significant technological trends driving the rise of deep learning; build, train, and apply fully connected deep neural networks; implement efficient (vectorized) neural networks; identify key parameters in a neural network’s architecture; and apply deep learning to your own applications.
The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI.
Introduction to Deep Learning
Analyze the major trends driving the rise of deep learning, and give examples of where and how it is applied today.
Neural Networks Basics
Set up a machine learning problem with a neural network mindset and use vectorization to speed up your models.
Shallow Neural Networks
Build a neural network with one hidden layer, using forward propagation and backpropagation.
Deep Neural Networks
Analyze the key computations underlying deep learning, then use them to build and train deep neural networks for computer vision tasks.
Gregory J Hamel ( Life Is Study) completed this course and found the course difficulty to be easy.
Neural Networks and Deep Learning is the first course in a new deep learning specialization offered by Coursera taught by Coursera founder Andrew Ng. The 4-week course covers the basics of neural networks and how to implement them in code using Python...
Neural Networks and Deep Learning is the first course in a new deep learning specialization offered by Coursera taught by Coursera founder Andrew Ng. The 4-week course covers the basics of neural networks and how to implement them in code using Python and numpy. The course page states that it only requires basic Python programming knowledge, although any experience you have with machine learning, linear algebra and calculus will be helpful with gaining a deeper understanding of the material. You can access the quizzes and programming assignments without paying for the full course, but if you want to submit them for grading and get credit as having completed the course, you have to pay for the certificate.
Neural Networks and Deep Learning starts with a short introduction to deep learning in week 1, followed by 3 full weeks that build your understanding of neural networks by starting with logistic regression implemented with the same structure as a neural net in week 2, shallow nets in week 3 and deep nets in week 4. Key topics include computational graphs and derivatives on graphs, gradient descent, vectorizing code, neural network representations, activation functions, backpropagation and deep nets. The course touches on high level concepts and considerations to frame learning, but the majority of the content focuses on the low-level nuts and bolts of neural network structure and how to translate it into code.
Each week after the first has roughly 1-2 hours of lecture split up into 5 to 15 minute video segments. In each segment, Andrew Ng appears on screen and gives a brief overview of what the the video is going to cover and then he discusses the topic with voice-overs while writing on white slides, followed by a brief outro where he reappears and summarizes key takeaways. There is a lot of handwritten information and notation in the lectures, which means some students may find certain lectures difficult (or boring) to follow, but he explains things very well and the notation is there to help you gain a concrete understanding of the structure of neural nets and prepare you for working with them in the programming assignments. The production value of the videos is fairly low as the intros and outros seem to be recorded with a non wide screen SD camera and the vast majority of content is simply Ng writing on mostly blank slides. The production style is reminiscent of his original machine learning MOOC which was released back in 2012. Still, the logical organization of the content combined with Ng's masterful knowledge and lucid explanations means the relatively rudimentary production doesn't detract from the course's value. Weeks 1-3 also include an optional guest lectures with different "heroes of deep learning."
The programming assignments in Neural Networks and Deep Learning are very well done, providing great instructions, explanations and examples. You can access all of the assignments as a freeware student, so even though the course won't be listed as completed when you finish, you can still work through them and learn all the same things as paying students. The assignments are heavily structured, giving students complete code skeletons of all required functions and only requiring students to implement specific key lines of code which are described in detail. In other words, most of the difficulty in implementing neural nets--such as the logic and structure of the code and aligning matrix dimensions--is taken care of for you so you don't need to be a strong programmer to complete the assignments. This keeps the assignments moving along at a nice pace and should help keep students from getting stuck for too long and while you may struggle to implement neural nets from scratch yourself after completing this course, it shows you the tools you would need to do it. And perhaps more importantly, it gives you insight into how neural nets are working under the hood, which is good to know even if you end up using a package to build them.
Neural Networks and Deep Learning is the best introductory course on neural networks on any of the main MOOC platforms that is accessible to about as broad a group of students as possible given the nature of the material. The course isn't perfect: notation-heavy videos can get tedious and it sometimes eschews mathematical details. It also makes a few questionable decisions such as putting a 40 minute interview of Geoffrey Hinton at the end of the first week, most of which you will not understand unless you've seen neural networks before and have familiarity with his work. That said, if you want to learn about neural networks and how to make them in code, this is the right place to start.
I give Neural Networks and Deep Learning 5 stars out of 5: Excellent.
Ronny De Winter completed this course, spending 5 hours a week on it and found the course difficulty to be medium.
The first excellent course of Andrew Ng's specialization on deep learning. WOW, this guy, the godfather of machine learning education (and co-founder of Coursera), knows how to educate the masses on one of the hottest technology topics in recent years....
The first excellent course of Andrew Ng's specialization on deep learning. WOW, this guy, the godfather of machine learning education (and co-founder of Coursera), knows how to educate the masses on one of the hottest technology topics in recent years.
Like no others, he understands how to teach the topic with the right level of math (the minimum you need to conceptually understand the topics and build solutions), the right balance between theory and practice, well thought and excellent built exercises and assignments, enough spaced repetition to make it stick.
The Jupyter notebooks are of very high quality and offer you a great learning experience.
And don't forget to check the discussion forums. Unlike many of Coursera's forums, this one is quite vivid with good additional material and discussions.
With this course, Andrew Ng shows us that the high quality of the pioneering MOOC years can still be reached today, top material like this can still be educated Massively. The world needs more of this.
Adail Retamal completed this course, spending 4 hours a week on it and found the course difficulty to be medium.
Having completed his classic Machine Learning course a few months earlier, I had all the concepts and intuitions still fresh in my mind, so I could go quickly through the lectures, quizzes and assignments. I really enjoyed it and highly recommend it for anyone interested on ML, Deep Learning and AI! I'm doing the entire specialization and couldn't be more satisfied!
I particularly enjoyed Andrew Ng's first course of the Deep Learning specialization because of its interactivity. Like any other programming course should be, we had to complete programming assignments as Jupyter Notebooks in the browser. We did not have...
I particularly enjoyed Andrew Ng's first course of the Deep Learning specialization because of its interactivity. Like any other programming course should be, we had to complete programming assignments as Jupyter Notebooks in the browser. We did not have to install anything on the computer so there were virtually no hardware or software requirements.
The assignments blend well with the lectures and there is a lot of code that's already included so you would have to work your way out with the rest.
There were some issues with grading the assignments, but after a few submissions, the grader graded them correctly.
This course is complex, as it requires some solid knowledge of linear algebra, calculus, and Python programming. So, I would say it's not for beginners.
It is designed for beginners in deep learning who have a background in basic python and linear algebra. Well planned, lets you develop intuitions about neural networks , also has optional video series on heroes of deep learning which is quite cool. People with some knowledge on NN might find it slow, but a good refresher. The Deep Learning specialization, which it is part of, is quite comprehensive too!
Raivis Joksts completed this course, spending 4 hours a week on it and found the course difficulty to be easy.
I took this course with some prior background in the subject, including Python deep learning libraries. This is rather math (calculus) heavy course, but in order to understand the basic concepts and logic, and complete the course, one does not need to fully understand how formulas work - just what is the objective of using this step or that step in the algorithm. Overall, one of the best introductory materials on deep learning. For those still struggling I recommend to star with Khan's Academy intro lectures on deep learning.
Chaitanya Kale completed this course, spending 4 hours a week on it and found the course difficulty to be easy.
It's a great course to understand basics of deep learning with a detailed walkthrough of gradient descent algorithm, forward propagation, backward propagation, cost and activation functions with logistic regression as a starting point.
Anonymous completed this course.
Its great ! It teaches you to build a simple neural network from scratch, the assigbments were very illustrative and it was a very good thing that the assignments are solved on the cloud using jupyter
Notebooks without the need to download the data
Vijayabhaskar completed this course, spending 4 hours a week on it and found the course difficulty to be medium.
The Best Course on the internet to study about Artificial Neural Networks,you just need to know basic high school calculus and linear algebra to finish this course.Well structured and the programming assignments are so helpful!
Great course. Builds the concepts step by step.
End of the course have a good comfort of forward prop , back prop and build a shallow neural network and deep neural network using python numpy. Highly recommend for anyone pursuing deep learning
Daniel Rosquete completed this course, spending 4 hours a week on it and found the course difficulty to be medium.
The course was good, Andrew NG is undoubtedly a great mind with too much knowledge, however, all the lessons were written on a white board. Is not that bad, but is not the easiest way to learn nevertheless.
Uğur Kaplan is taking this course right now, spending 4 hours a week on it and found the course difficulty to be medium.
It is good course even though there is redundancy in it. I guess Andrew Ng repeats the concepts he finds important so students can understand. But that much repetition kills the flow, in my opinion.
Anonymous completed this course.
Great course! I really liked how systematically Andrew Ng goes through this broad field. You probably won't learn everything there is in the real of Deep Learning just by taking this course (I think that would be impossible) but you will get a rock solid (trusted) foundation for the important parts to expand that knowledge and keep up with latest progress on your own afterwards.
Anonymous completed this course.
Great introduction to the nuts and bolts of neural networks. Not math intensive but enough to give you more than an intuition of what’s happening under the hood. Notebooks with boilerplate code allow for targeted and efficient learning.
Anonymous completed this course.
Totally enjoyed this class! I consider Andrew Ng one of the best instructors in this field. The class will actually have you write code weekly and your own deep neural network. Highly recommend it.