subject
Intro

Coursera: Neural Networks for Machine Learning

 with  Geoffrey Hinton
Learn about artificial neural networks and how they're being used for machine learning, as applied to speech and object recognition, image segmentation, modeling language and human motion, etc. We'll emphasize both the basic algorithms and the practical tricks needed to get them to work well.

This course contains the same content presented on Coursera beginning in 2013. It is not a continuation or update of the original course. It has been adapted for the new platform.

Please be advised that the course is suited for an intermediate level learner - comfortable with calculus and with experience programming (Python).

Syllabus

Introduction
Introduction to the course - machine learning and neural nets

The Perceptron learning procedure
An overview of the main types of neural network architecture

The backpropagation learning proccedure
Learning the weights of a linear neuron

Learning feature vectors for words
Learning to predict the next word

Object recognition with neural nets
In this module we look at why object recognition is difficult.

Optimization: How to make the learning go faster
We delve into mini-batch gradient descent as well as discuss adaptive learning rates.

Recurrent neural networks
This module explores training recurrent neural networks

More recurrent neural networks
We continue our look at recurrent neural networks

Ways to make neural networks generalize better
We discuss strategies to make neural networks generalize better

Combining multiple neural networks to improve generalization
This module we look at why it helps to combine multiple neural networks to improve generalization

Hopfield nets and Boltzmann machines


Restricted Boltzmann machines (RBMs)
This module deals with Boltzmann machine learning

Stacking RBMs to make Deep Belief Nets


Deep neural nets with generative pre-training


Modeling hierarchical structure with neural nets


Recent applications of deep neural nets


22 Student
reviews
Cost Free Online Course (Audit)
Pace Upcoming
Institution University of Toronto
Provider Coursera
Language English
Certificates Paid Certificate Available
Hours 7-9 hours a week
Calendar 16 weeks long
Sign up for free? Learn how

Disclosure: To support our site, Class Central may be compensated by some course providers.

+ Add to My Courses
FAQ View All
What are MOOCs?
MOOCs stand for Massive Open Online Courses. These are free online courses from universities around the world (eg. Stanford Harvard MIT) offered to anyone with an internet connection.
How do I register?
To register for a course, click on "Go to Class" button on the course page. This will take you to the providers website where you can register for the course.
How do these MOOCs or free online courses work?
MOOCs are designed for an online audience, teaching primarily through short (5-20 min.) pre recorded video lectures, that you watch on weekly schedule when convenient for you.  They also have student discussion forums, homework/assignments, and online quizzes or exams.

22 reviews for Coursera's Neural Networks for Machine Learning

Write a review
16 out of 17 people found the following review useful
3 years ago
Bobby Brady partially completed this course, spending 6 hours a week on it and found the course difficulty to be very hard.
This is one of those chance in a lifetime courses you have to get to learn from the greats. Geoffrey Hinton was one of the most important and influential researchers to work on artificial intelligence and neural nets back in the 80's. Currently he is working with Google in their AI/deep learning initiatives. The lec Read More
This is one of those chance in a lifetime courses you have to get to learn from the greats. Geoffrey Hinton was one of the most important and influential researchers to work on artificial intelligence and neural nets back in the 80's. Currently he is working with Google in their AI/deep learning initiatives.

The lectures are complex but Geoffrey does a really good job of providing detailed explanations. The course is mostly theory based and heavy on calculus and linear algebra with only a few programming exercises. I would categorize this within the same space as Yaser Abu-Mostafa's Learning From Data.

There were 15 total quizzes of which you only had 2 attempts. Since i was had very little experience with Calculus and was still cutting my teeth on Python i had to let this one go. I plan on taking this again at some point in the future, but it looks the course has been archived.
Was this review helpful to you? YES | NO
a month ago
Pedro Q is taking this course right now and found the course difficulty to be medium.
I honestly can't understand the multiple 5 star reviews presented on this site about the course. I'm giving it a 1 star which is a bit harsh I know but I'm doing it to offset the number of 5 star reviews here. Honestly I think the course deserves something between 2 and 3 stars depending on your approach to it. Yes P Read More
I honestly can't understand the multiple 5 star reviews presented on this site about the course. I'm giving it a 1 star which is a bit harsh I know but I'm doing it to offset the number of 5 star reviews here. Honestly I think the course deserves something between 2 and 3 stars depending on your approach to it.

Yes Prof. Hinton is a leading expert in the field but the course materials and the way they are presented are pretty bad! I started the course already with a decent foundation on machine learning wanting to learn more about the specifics of neural nets but it ended up in confusing me more on core concepts. For instance I was reasonably sure about how backpropagation worked until I got to the part in this course about it, which managed to confuse me so much that I had to go look up multiple sources to relearn it again. This happened with a number of different concepts over the course and it's not that the course is "challenging" as some people here say, it's really a question of poor explanations and poor organization of materials (the quizzes are challenging in the sense that they demand a much better grasp on the material than what the lectures give you but this is one of the few positive points in my view).

And sure you can always research things by yourself, and this is a good practice regardless, but in this case it's an absolute necessity because of the poor lectures. In a sense maybe it is it's redeeming feature. It can piss you off so much to be confused in the lectures that you can go and learn the material on your own just out of spite! It can work, but a truly good course that would deserve 5 stars shouldn't have to rely on this!

I actually dropped from the course for a few months after a terrible week 4 and recently out of sheer stubbornness I am trying to complete it, but it feels like a terrible grind. Basically if you already know enough to understand this course well you probably didn't need it anyway but if you don't I would stay away if you have no other alternative as with the wrong approach it seems to confuse more than it helps.
Was this review helpful to you? YES | NO
7 out of 8 people found the following review useful
3 years ago
profile picture
Kiran Karkera completed this course, spending 10 hours a week on it and found the course difficulty to be hard.
Prof. Hinton is one of the leading lights of Neural Networks, an area of ML research that had been relegated to the sidelines in the 80s and 90s but is now in the limelight thanks to recent advances in the field. The basic ML course does dip its toes in the neural networks pool, but this course (but naturally) goes mu Read More
Prof. Hinton is one of the leading lights of Neural Networks, an area of ML research that had been relegated to the sidelines in the 80s and 90s but is now in the limelight thanks to recent advances in the field.

The basic ML course does dip its toes in the neural networks pool, but this course (but naturally) goes much deeper. The material as well as the instructor are excellent, and the course lectures are punctuated by Prof. Hinton’s deadpan humour. This course requires a little mathematical background (such as a calculating derivatives for backpropagation) but the math is explained quite nicely.

My only suggestion in this course would be to have more programming assignments (there were only 4 in the first edition), however, the quizzes do require some programming to answer questions.
Was this review helpful to you? YES | NO
12 months ago
profile picture
Sha Liu completed this course, spending 5 hours a week on it and found the course difficulty to be very hard.
Yes there're negative reviews saying this course is poorly designed, too hard to follow, confusing, but after finishing it and earn the certificate I think I make the right call. Actually, I agree with some of the reviews above. This course is not as polished as other pillar courses on Cousera like Andrew Ng's machine Read More
Yes there're negative reviews saying this course is poorly designed, too hard to follow, confusing, but after finishing it and earn the certificate I think I make the right call.

Actually, I agree with some of the reviews above. This course is not as polished as other pillar courses on Cousera like Andrew Ng's machine learning. Yet, this the best course I can find to teach me advanced neural network topics in a mooc style, I mean with lectures, quizzes and assignments. And I this style matters to me because I find it hard to learn things in depth just by reading text books (though often enjoyable).

Not to mention that professor Hinton is an authoritative in this field and would cover a lot of background, with anecdote sometimes and help you understand how the machine learning evolves into what it is today (to be exact it's 2012).

I enrolled this course right after I finished Andrew's machine learning and I found a hard time adjusting my learning attitude. Now I feel that if you're really serious about machine learning and neural network, and like me you know nothing about it before, then it's a must you take this course. Why? Just think about all the researchers working on this area and you could get an insight into their best work in such a short time. If that's not what you want, instead you just want a brief overview of deep learning without getting into calculus and probabilities, then choose something else.

In short, whether you should take it depends what you want from the course and what it provides. For me, I want to be serious about it and so I feel the frustration and hiccups I experienced during this course compared what i have learning is nothing to what a real researcher might have experienced. I better finish this review soon and go through this course a second time 'coz I feel uneasy that I only understand 50% but get 100% grade.
Was this review helpful to you? YES | NO
7 months ago
Bill Griffith partially completed this course.
Prof. Hinton may be one of the leading lights of Neural Networks, but the style of this course will prove to discourage any novice who hopes to gain insight into theory behind neural networks. According to Prof. Hinton himself, he put this course together in his spare time, and I believe that the poor quality of the Read More
Prof. Hinton may be one of the leading lights of Neural Networks, but the style of this course will prove to discourage any novice who hopes to gain insight into theory behind neural networks. According to Prof. Hinton himself, he put this course together in his spare time, and I believe that the poor quality of the material reflects his effort. I agree with the other reviewer, it's a horrible course. Very few examples, no diagrams, no mathematical detail. Prepare to do a lot of discovery on your own from other sources in order to pass this course.
Was this review helpful to you? YES | NO
8 months ago
profile picture
Anonymous is taking this course right now.
Just horrible. The quality of the material course is very poor. The covered field is very interesting but the course is not intelligible. The course of Andrew Ng was very clear but this one, you must take course about neural network to be able to understand. Very few schema, no example, no diagram. You have to be very very motivated.
Was this review helpful to you? YES | NO
9 months ago
Dolly Ye is taking this course right now, spending 8 hours a week on it and found the course difficulty to be hard.
Geoff Hinton is one of the founding fathers of neural network when everyone jumped ships in the 90s.This course takes a more theoretical and math-heavy approach than Andrew Ng's Coursera course.If you are interested in the mechanisms of neural network and computer science theories in general,you should take this! An intellectually invigorating experience.
Was this review helpful to you? YES | NO
7 months ago
profile picture
Jakub completed this course, spending 6 hours a week on it and found the course difficulty to be very hard.
This is one of the hardest MOOC I ever took, even though prof. Hinton is a great researcher, some topics lack explanation so additional resources are required (sometimes they are provided). Biggest problems are technical ones like error in quiz and unavailable lecture note mentioned in the video.

Overall this is still very valuable course with lots of knowledge.
Was this review helpful to you? YES | NO
2 out of 3 people found the following review useful
2 years ago
Pablo Torre completed this course, spending 10 hours a week on it and found the course difficulty to be very hard.
This is a hard class, it goes deep into the math behind neural networks and it goes deep into the design implementation of such network. It is also a unique opportunity to learn from someone who is a pioneer and one of the lead thinkers in the field of neural nets.
Was this review helpful to you? YES | NO
2 out of 2 people found the following review useful
5 years ago
profile picture
Anonymous completed this course.
If you interested in neural networks, this course may discover you a whole new world of possibilities. It is not easy, but is is definitely worth the effort.
Was this review helpful to you? YES | NO
3 months ago
Jae-seung Lee completed this course, spending 3 hours a week on it and found the course difficulty to be medium.
I would recommend this course to anyone who is serious about learning neural networks. I've got a better understanding of the concept, history, and techniques, which may not be available in other online courses or may not be easily grasped by reading papers only.
Was this review helpful to you? YES | NO
9 months ago
Lanting Guo completed this course.
Was this review helpful to you? YES | NO
0 out of 2 people found the following review useful
2 years ago
Colin Khein completed this course.
Was this review helpful to you? YES | NO
a year ago
profile picture
Stephane Mysona completed this course.
Was this review helpful to you? YES | NO
a year ago
Hari Narain R completed this course.
Was this review helpful to you? YES | NO
0 out of 2 people found the following review useful
2 years ago
profile picture
Nihal Balani completed this course.
Was this review helpful to you? YES | NO
a year ago
Josh partially completed this course.
Was this review helpful to you? YES | NO
0 out of 1 people found the following review useful
2 years ago
Lindsay Rich Fagerlee is taking this course right now.
Was this review helpful to you? YES | NO
a year ago
Christopher Pitt completed this course.
Was this review helpful to you? YES | NO
0 out of 1 people found the following review useful
2 years ago
profile picture
Adrian Borucki completed this course.
Was this review helpful to you? YES | NO
Was this review helpful to you? YES | NO
0 out of 3 people found the following review useful
2 years ago
Robert Stahr partially completed this course.
Was this review helpful to you? YES | NO

Class Central

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free