#19 overallClassic
Neural Networks for Machine Learning (Geoffrey Hinton)
Coursera
25 recommenders · 32 threads · recommended in 11 years, 2012–2025 · score 35.0
Geoffrey Hinton's Coursera course on neural networks for machine learning, covering feedforward and recurrent networks, backpropagation, and deep learning fundamentals from one of the field's pioneers. It is a graduate-level course with a theoretical lean and demanding exercises.
Commenters call it an excellent, challenging introduction to neural networks taught by a pioneer, and several say it changed the course of their careers.
Machine Learning & AIadvancedfreevideo lectures#neural networks#backpropagation#deep learning#hinton#machine learning
Recommendations by year
20062026
Geoff Hinton's 2012 Coursera course "Neural Networks for Machine Learning" was incredible. Anyone who took that course got in on the ground floor of deep learning just when it was about to take off. It certainly changed the course of my career.
To give an idea of how cutting-edge it was at the time, the well-known RMSProp optimizer was unpublished work that Hinton presented in the course, and people had to cite the presentation slides when they used it in papers published later.
Geoffrey Hinton had an excellent series on neural networks from 2011 for Coursera available here https://m.youtube.com/playlist?list=PLoRl3Ht4JOcdU872GhiYWf6... detailing the fundamentals of machine learning. The series was later wholesale replaced by another led by Andrew Ng of Google. I really adored Geoffrey’s lectures and recommend it to anyone looking to get into the space. It ends with him hinting at the idea of attention networks, but sadly I can’t find any later lectures from him on the topic.
I took Geoff Hinton's Coursera course on neural nets when it was first offered and it was incredible. No exaggeration to say it changed the course of my career. That's all to Geoff's credit of course, not Coursera per se. But the idea that you can get instruction from the world's foremost expert in a topic rather than whoever your university happened to hire, or even if you're not in university at all, is pretty disruptive.
Andrew Ng's class was great! For a tougher class that focuses on one of the technologies, I recommend Geoffrey Hinton's "Neural Networks for Machine Learning" on Coursera. Really eye opening for me, and fairly close to the leading edge in deep learning, as far as I can tell. I felt that the exercises were more detailed and challenging than in Ng's class, and thus I ended up learning more.
I took Geoff Hinton's Coursera course about 3 years ago, and it remains my favourite online course I've ever taken. While I do understand that it may have felt a bit theoretical and heavy, I also think that this theory is more important to understand in neural networks than in other areas of ML e.g. for debugging issues. I also loved his wry sense of humour and turn of phrase.
I felt that Andrew Ng left out a lot of the details that I was curious about. For example, I remember he introduces logistic regression and cross-entropy, but he kind of just writes down the equations and says they differentiate nicely, he never explains where they actually come from, or even points the interested viewer where to look for more information (short answer : information theory, also this post https://terrytao.wordpress.com/2016/06/01/how-to-assign-part... is a great explanation for cross entropy)
The answer to this question depends on your level of computer & math proficiency. Some folks here have been debating about the relative merits of practice vs. theoretical foundations, but this dispute makes some assumptions about where you are starting from and where you are most comfortable. The fastest way to learn something is to fit it into a framework that you already understand. If you have a PhD in theoretical physics/abstract mathematics (like a lot of ML researchers), then the more mathematical (theoretical) frameworks will be a good way to build deep intuitions. If, on the other hand, you are more into applied data analysis, then you will probably find that working on applications will be the easiest way to go.
Personally, I enjoyed both Andrew Ng's and Geoffrey Hinton's respective courses on ML and Neural Networks on Coursera. You may also want to check out Michael Neilsen's online essay on deep learning (http://neuralnetworksanddeeplearning.com). Ultimately I would also encourage you to supplement your understanding by applying this work to your own applications. The universe is often the best teacher.
Here are the resources I found useful: ========================================== Advices from Open AI, Facebook AI leaders
Courses You MUST Take:
Machine Learning by Andrew Ng (https://www.coursera.org/learn/machine-learning) /// Class notes: (http://holehouse.org/mlclass/index.html)
Yaser Abu-Mostafa’s Machine Learning course which focuses much more on theory than the Coursera class but it is still relevant for beginners.
(https://work.caltech.edu/telecourse.html)
Neural Networks and Deep Learning (Recommended by Google Brain Team) (http://neuralnetworksanddeeplearning.com/)
Probabilistic Graphical Models (https://www.coursera.org/learn/probabilistic-graphical-model...)
Computational Neuroscience (https://www.coursera.org/learn/computational-neuroscience)
Statistical Machine Learning (http://www.stat.cmu.edu/~larry/=sml/)
From Open AI CEO Greg Brockman on Quora
Deep Learning Book (http://www.deeplearningbook.org/) ( Also Recommended by Google Brain Team )
It contains essentially all the concepts and intuition needed for deep learning engineering (except reinforcement learning). by Greg
2. If you’d like to take courses: Linear Algebra — Stephen Boyd’s EE263 (Stanford) (http://ee263.stanford.edu/) or Linear Algebra (MIT)
(http://ocw.mit.edu/courses/mathematics/18-06sc-linear-algebr...)
Neural Networks for Machine Learning — Geoff Hinton (Coursera) https://www.coursera.org/learn/neural-networks
Neural Nets — Andrej Karpathy’s CS231N (Stanford)
http://cs231n.stanford.edu/
Advanced Robotics (the MDP / optimal control lectures) — Pieter Abbeel’s CS287 (Berkeley)
https://people.eecs.berkeley.edu/~pabbeel/cs287-fa11/
Deep RL — John Schulman’s CS294–112 (Berkeley) http://rll.berkeley.edu/deeprlcourse/
Geoff Hinton's Coursera course was what got me into it. It's not for the faint of heart. I might recommend Andrej Karpathy's cs231n as a more up to date source today.
Yes, I did my research but there is no such interactive tutorial online like Treehouse or Codecademy. There are so many tutorials but none of it tells you the whole path.
Here are the resources I found useful:
========================================== Advices from Open AI, Facebook AI leaders
Courses You MUST Take: Machine Learning by Andrew Ng (https://www.coursera.org/learn/machine-learning) /// Class notes: (http://holehouse.org/mlclass/index.html)
Yaser Abu-Mostafa’s Machine Learning course which focuses much more on theory than the Coursera class but it is still relevant for beginners.(https://work.caltech.edu/telecourse.html)
Neural Networks and Deep Learning (Recommended by Google Brain Team) (http://neuralnetworksanddeeplearning.com/)
Probabilistic Graphical Models (https://www.coursera.org/learn/probabilistic-graphical-model...)
Computational Neuroscience (https://www.coursera.org/learn/computational-neuroscience)
Statistical Machine Learning (http://www.stat.cmu.edu/~larry/=sml/)
From Open AI CEO Greg Brockman on Quora
Deep Learning Book (http://www.deeplearningbook.org/) ( Also Recommended by Google Brain Team )
It contains essentially all the concepts and intuition needed for deep learning engineering (except reinforcement learning). by Greg
2. If you’d like to take courses: Linear Algebra — Stephen Boyd’s EE263 (Stanford) (http://ee263.stanford.edu/) or Linear Algebra (MIT)(http://ocw.mit.edu/courses/mathematics/18-06sc-linear-algebr...)
Neural Networks for Machine Learning — Geoff Hinton (Coursera) https://www.coursera.org/learn/neural-networks
Neural Nets — Andrej Karpathy’s CS231N (Stanford) http://cs231n.stanford.edu/
Advanced Robotics (the MDP / optimal control lectures) — Pieter Abbeel’s CS287 (Berkeley) https://people.eecs.berkeley.edu/~pabbeel/cs287-fa11/
Deep RL — John Schulman’s CS294–112 (Berkeley) http://rll.berkeley.edu/deeprlcourse/
From Director of AI Research at Facebook and Professor at NYU Yann LeCun on Quora
In any case, take Calc I, Calc II, Calc III, Linear Algebra, Probability and Statistics, and as many physics courses as you can. But make sure you learn to program.
Agreed, cs231n is a great course. For neural net information less specific to computer vision I would also recommend looking up video lectures from Nando de Freitas and/or Hugo Larochelle.
I also have to put in a plug for Geoff Hinton's Coursera course. It's not for the faint of heart. It's essentially a graduate level college course with the commensurate required time investment. It's getting a little old now but it was my introduction to neural nets and if you want to learn from a pioneer in the field it's still a good option in my opinion: https://www.coursera.org/learn/neural-networks
If it isn't too introductory, I'd say take the Andrew Ng course on Machine Learning on Coursera. If that's too introductory, try the Geoffrey Hinton course on Neural Networks on Coursera, or the Google / Tensorflow course on Deep Learning on, er, I think it's EdX.
I can highly recommend Hinton's course on Coursera - https://www.coursera.org/learn/neural-networks
It starts on October 31st, I took it a while ago and learned a lot. The course is gravitating towards the theoretical end of the spectrum. If you want something thats a bit easier to get into, I can recommend the course by Hugo Larochelle:
http://info.usherbrooke.ca/hlarochelle/neural_networks/conte...
You can start with free coursera course https://www.coursera.org/learn/machine-learning/, it starts 17 oct
and then continue with https://www.coursera.org/learn/neural-networks/
How about the textbook http://www.deeplearningbook.org/.
It introduces you to some of the underlying principles which haven't changed much over time. I highly recommend it if you want to get deeper intuitions on the principles of CNN, LSTM/RNN, Restricted Boltzmann Machines etc. Also, Hinton's Coursera lectures, though not sure if you can access it anymore.
it's very good, but personally I'd start with the Andrew Ng and Hinton courses
https://www.coursera.org/learn/machine-learning https://www.coursera.org/learn/neural-networks
I think the Udacity course is best if you know principles of machine learning and want to apply them in a more professional toolchain and learn Tensorflow
Greg Brockman (Founder of Open AI) has written this amazing answer:
If you want to read one main resource... the Goodfellow, Bengio, Courville book (available for free from http://www.deeplearningbook.org/) is an extremely comprehensive survey of the field. It contains essentially all the concepts and intuition needed for deep learning engineering (except reinforcement learning).
If you'd like to take courses... Pieter Abbeel and Wojciech Zaremba suggest the following course sequence:
- Linear Algebra — Stephen Boyd’s EE263 (Stanford) - Neural Networks for Machine Learning — Geoff Hinton (Coursera) - Neural Nets — Andrej Karpathy’s CS231N (Stanford) - Advanced Robotics (the MDP / optimal control lectures) — Pieter Abbeel’s CS287 (Berkeley) - Deep RL — John Schulman’s CS294-112 (Berkeley)
(Pieter also recommends the Cover & Thomas information theory and Nocedal & Wright nonlinear optimization books).
If you'd like to get your hands dirty... Ilya Sutskever recommends implementing simple MNIST classifiers, small convnets, reimplementing char-rnn, and then playing with a big convnet. Personally, I started out by picking Kaggle competitions (especially the "Knowledge" ones) and using those as a source of problems. Implementing agents for OpenAI Gym (or algorithms for the set of research problems we’ll be releasing soon) could also be a good starting place.
Quora link: https://www.quora.com/What-are-the-best-ways-to-pick-up-Deep...
It sounds like you've got the beginnings of Machine Learning (classification & regression), but I'd still recommend checking out Coursera. The JHU Data Science series is good, but more geared towards DS than AI. There are others on there as well; if you're looking to get into deep learning, I echo the recommendation to check out Ng's course, though this might be good, too: https://www.coursera.org/course/neuralnets
Geoffrey Hinton's "Neural Networks for Machine Learning" on Coursera [0] is a pretty excellent course to cover the basics. There's a lot in the course, but if you just skim over the videos you'll get a pretty good "big picture" view of what's out there. As with any quantitive topic, it's best to take a first pass where you just glance at the math and come back later to really focus on the missing pieces
An important thing to realize is that much of deep learning is decades old neural networks research that has for one reason or another become more viable recently.
Andrew Ng's Coursera course on Machine Learning:
https://www.coursera.org/learn/machine-learning
There's also this course on Neural Networks by Geoffrey Hinton:
https://www.coursera.org/course/neuralnets
If you do the Andrew Ng course, you'll have to learn/know Octave (or Matlab). Otherwise, Python is very heavily used in ML these days and you could do a lot worse than learning Python. R and Octave are both very useful as well. And, as you note, there is a lot of machine learning software available in the JVM world as well. Scala in particular seems to be gaining some ground in this world.
Find a problem to work on in a domain you find interesting. By reading published papers and trying to attack the problem, you'll be forced to pick up a lot of other knowledge not commonly discussed like: feature extraction and selection, dimensionality reduction, dealing with sparsity, common metrics for that problem, recent work, etc.
I was forced to learn a massive amount in a short period of time for work, but I'd previously watched Andrew Ng's lectures, as well as majored in Math/CS. I can also generally recommend Hinton's NN lectures, Socher's Deep learning for NLP, Andrew Ng's Machine Learning, and a few books.
I have recently wrote an article collecting the best AI resources:
https://medium.com/@rayalez/best-deep-learning-resources-76b...
Specifically, I would reccommend AIMA as the best introduction to AI in general, and a fantastic video course from Berkeley:
https://www.youtube.com/channel/UCshmLD2MsyqAKBx8ctivb5Q/vid...
and also Andrew Ng's course on coursera:
https://www.coursera.org/course/ml
For neural networks there's an awesome course by Hinton:
https://class.coursera.org/neuralnets-2012-001/lecture
and UFLDL tutorial:
http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutori...
This is an excellent course no matter which language you prefer:
https://class.coursera.org/neuralnets-2012-001/lecture
There is a nice book by my profs (Y. Bengio, A. Courville) and a former student of the lab (I. Goodfellow) here: http://www.iro.umontreal.ca/~bengioy/DLbook/ The chapter on RNNs is pretty enlightening. You probably want to start with something the goes through feedforward networks, convolutional, etc. first though.
Andrew Ng's Coursera course does a super basic NN in MATLAB which might be good to shake the rust off [1]. Hugo Larochelle's youtube course [2], Geoff Hinton's Coursera course [3], and Nando's youtube Deep Learning course [4] are all very good. There are also some great lectures from Aaron Courville from the Representation Learning class that just finished here at UdeM [5]
If you want to do this for real (not self teaching RNN backprop on toy examples) tool-wise you generally go with either Theano (my preference) or Torch - implementing the backwards path for these (and verifying gradients are correct) is not pretty.
Theano does it almost for free, and Torch can do it at the module level. Either way you definitely want one of the higher order tools!
[1] https://www.coursera.org/learn/machine-learning
[2] https://www.youtube.com/watch?v=SGZ6BttHMPw&list=PL6Xpj9I5qX...
[3] https://www.coursera.org/course/neuralnets
[4] https://www.youtube.com/watch?v=PlhFWT7vAEw
[5] https://ift6266h15.wordpress.com/
I probably made a career direction error in the early 1990s. I had been on DARPA'S neural network tools advisory panel and written the SAIC Ansim product, but moved on because of a stronger interest in natural language processing. Now, I think deep learning is getting very interesting for NLP.
This UCB project looks awesome!
BTW, I took Hinton's Coursera neural network class a few years ago, and it was excellent. Take it if that course is still online.
I would recommend going through the CalTech Course - Learning from Data run by Yasir Abu Mustafa as the first step. https://www.edx.org/course/learning-data-caltechx-cs1156x#.V...
It is one of the best places to start. Please see that the course will require you to spend considerable time. If you find this challenging, you can also look at the Machine Learning class by Andrew Ng on Coursera.
Once you have undergone these courses, you can take up Coursera course on Neural Nets or look at tutorials on deeplearning.net
Bookwise, Yoshua Bengio, Aaron Courville, and Ian Goodfellow are nearly finished with their MIT Press book on deep learning: http://www.iro.umontreal.ca/~bengioy/dlbook/ . It is pretty strong on the true theory of what is going on in deep networks, and has fairly good intuition for how and why things work. Paired with the deep learning tutorials http://www.deeplearning.net/tutorial/, as well as the content from UFLDL it is a pretty strong foundation for advanced study.
Michael's book seems to target a more introductory level - a beginner might be better off to start with that, follow with Andrew Ng's ML course, which has a section on neural nets including an assignment implementing backpropagation, then continue with the deep learning book and the {deep learning, UFLDL} tutorials. This should be solid enough to at least read most of the cutting edge work and papers, if that is the aim.
Hugo Larochelle's youtube course https://www.youtube.com/playlist?list=PL6Xpj9I5qXYEcOhn7Tqgh... and Hinton's coursera course https://www.coursera.org/course/neuralnets are also great references.
Geoffrey Hinton (a notable deep learning researcher) did a coursera course on neural networks awhile ago. It's over but you can still see the lectures which are very good: https://www.coursera.org/course/neuralnets
Metacademy is also a very useful resource for anything machine learning: http://www.metacademy.org/
I love looking at the results and seeing the annual improvement and breakout strategies. Deep learning has really come into its own during the last eight years.
People interested in learning about some of the techniques employed (CNNs and deep networks) are encouraged to take Geoff Hinton's Coursers course [1], which does a really good job of covering modern techniques from one of their pioneers.
[1] https://www.coursera.org/course/neuralnets
In Hinton's Coursera class, which was very good, he made a strong point about GPUs being the way to go (at least for now) in building deep learning networks.
DeepLearning4j author here. I'd just like to add that despite training neural networks being hard, they are great for understanding data if trained right.
There are a lot of innovations in image processing wrt neural nets specifically. The right neural network can learn everything from scene detection to simple object recognition.
I would highly reccommend taking a look at the neural nets course on coursera to understand some of the use cases.
Companies are quite desperate to find data scientists, I am sure they will hire anyone who can do the job properly, self-taught or not :) You may want to do more than one class before applying to jobs though - for instance check out stuff like Geoffrey Hinton's course on Neural Networks for Machine Learning https://www.coursera.org/course/neuralnets, plus general CS & Stats classes if you don't have a CS or Maths degree.
I've not had the time to go through the Hinton course fully myself, but the Coursera link is still up - https://www.coursera.org/course/neuralnets
You should still be able to register/download the materials. That's what I did.
I posted this because it is a good counter point to the very optimistic New York Times article from a few days ago.
BTW, I just finished the final exam for Hinton's Coursera neural network class an hour ago. Nice class, and I would recommend it if he offers it again. His lectures were especially interesting.
I don't doubt that there are people working at EdX / Coursera with a passion for education. I just think maybe these companies are moving in a direction that is at odds with the goal of providing free education, everywhere, to everyone, at any stage in their life.
I enrolled in some of the earliest MOOCs. Sebastian Thrun's original ai-class.com which now redirects to Udacity. I took the first iteration of Andrew Ng's "Machine Learning" on Coursera, as well as Geoffrey Hinton's original NNML course. Back then, everything was open. Course materials were shared freely, and the archives were available for years after the course concluded. There was an autograder for coding assignments that didn't get in your way too much.
Slowly, more and more roadblocks were put in place.
What was your experience like at Coursera? Did you get a chance to see how decisions about the UI and structure of courses were made? Did you get a sense of how much the marketing / business side of things interfered with the education side?
For who? Maybe these sites have created a product that works well for a certain niche of people, and they've hyper-optimized for that. Great. But that's not really the dream we all had for it ten years ago.
Like I said in a sibling comment: I've already been through school, and already know my own learning process. I find that the practices Coursera / EdX actively get in the way of my learning.
Language changes. Most people include in their meaning of "dark pattern" things like "artificially restricting you from performing actions that the website is fully capable of performing, with dubious or justification or malicious intent".
I don't think EdX is malicious, just that their reasons for restricting usage of course materials are dubious, and conflict with their stated mission.
Why can't it be a content library? I learn a lot at libraries!
This structure helps some people, sure. But some people like me are not full-time students. Some weeks I have lots of time to dig in, other weeks I don't have time to even watch a lecture. Moreover, I'm learning for myself, not for credentials, so why should I care what a website thinks of my progress?
I don't have definitive proof, but every time I visit the EdX or Coursera sites it just so happens that the exact course I was searching for started within a week of the current date. Maybe I'm being paranoid.
This was mostly a joke :)
Again, I'm not a student. I trust my own learning process, which is impeded by constant quizzes. I'm doing this to broaden my knowledge. I don't have time to enroll in a college class, but I have time to listen to a few lectures when doing dishes, and read a couple book chapters per week.
Coursera and others are technically capable of opening up their service to this use case -- it doesn't cost them anything -- so why not do it?
In a certain sense, online education is thriving! There are tons of video lectures on YouTube available for free and I can easily pirate any textbook I want to with a quick Google search. It's just that Coursera / EdX / etc don't really fit into that for me. I really wish they did.
Whoah!
Okay, counter-point: in my experience Udacity has the highest quality content on the toughest technical subjects. To me, it is evident that an enormous amount of work has gone into making the lectures and exercises effective.
Coursera has more courses, and the quality varies more but some of them are excellent. In any case, Coursera lectures come from university partners we are all familiar with, so people can decide if they like the Andrew Ng Machine Learning Class or Geoff Hinton on Neural Networks.
I am not affiliated with either of them.
Although IBM's hardware implementation does not support the current hotness in neural models, I still think that this is a big deal, both for applications with the current chip and also future improvements in even less required energy and smaller and more dense chips.
I was on a DARPA neural network tools advisory panel for a year in the 1980s, developed two commercial neural network products, and used them in several interesting applications. I more or less left the field in the 1990s but I did take Hinton's Coursera class two years ago and it is fun to keep up.
I pretty much agree, but I'd like to point out that, as a field, programming emphasizes the importance of "Smart and Gets Things Done" more than pretty much any other field does.
I've been interviewing lately, both at hardware and software companies. At microprocessor startups, I ask about the pedigree (past experience, not educational credentials) of pretty much everyone I meet. I don't do that at software companies. The reason is, you pretty much never hear about a new team successfully making a high-performance microprocessor. Apple bought PA Semi, which had a moderately successful exit, but PA Semi was basically the SiByte team, which left after SiByte was acquired by Broadcom, and SiByte was composed of key people from DEC who had been working together for over a decade. When you hear about a new team where most of the people are smart new grads, they usually spend ~ $100M over five or six years years, find that they don't have a competitive product (or, more likely, don't even have anything that's close to working). If they have funding left to burn they may pivot a couple times over the course of a couple years before they burn through their cash and implode.
And that's despite microprocessor design being close to pure reason, in the grand scheme of things. Experience and wisdom matter a lot more in most endeavors. Something you see a lot, even here on HN, when non-CS/programming/engineering topics make it to the front page, are people who try to extrapolate from a few "obvious" facts and then come up with a conclusion that's completely and totally wrong.
In software, you hear about successful companies founded by people just out of school, or even people who have dropped out of school, all the time. "Smart and Gets Things Done" can be good enough to make a decent product. But, something you'd never want to hear from a plumber or a carpenter is "well, I've read some books on the topic, and tried out some tools at home depot, plus I'm smart and good at hacking".
Things like carpentry, manufacturing, etc. are hard. They're done so well here (in developed countries) that it's easy to forget an idea of how hard they really are. If you want to get an idea of how hard they are to learn from scratch, consider South Korea after WII. Its GDP per capita was lower than Ghana, Kenya, and just barely above the Congo[1]. For various reasons, the new regime didn't have much baggage, and they wanted Korea to become a first-world nation. The story I've heard is that the government started by subsidizing concrete. After many years making concrete, they wanted to move up the manufacturing chain and start making ships (among other things). They pulled some of their best people who had experience in business (having learned skills like management, operations, etc.) from working in concrete to try to build ships. They knew they didn't have the expertise to do it themselves, so they contracted out the plans and got detailed instructions how to build ships. They got plans from Scotland, because Scotland has a long history of shipbuilding. Makes sense, right? But, when the Koreans tried to build ships with Scottish plans and detailed step-by-step directions, the result was two ship halves that didn't quite fit together and sunk when assembled. For historical and geographic reasons, Scotland's shipyards weren't full-sized, and they built their ships in two halves and then assembled them. Worked fine for them, because they'd be doing it at scale since the 1800s, and had world renowned expertise by the 1900s[2]. The Koreans eventually managed to start a shipbuilding industry by hiring foreign companies to come and, build ships locally, and show people how it's done. It took decades to what we would consider basic manufacturing working smoothly, even though all of the requisite knowledge existed in books, was taught in university courses, and could be had from experts for a small fee. "Smart and Gets Things Done" goes so much further in programming than it does in virtually any other non-academic field.
Today, anyone with a CS 101 background can take Geoffrey Hinton's course on neural networks and deep learning[3] and start applying state of the art machine learning techniques[4] to research grade problems within a couple months. But, if you want to build a ship, and you "only" have a decade of experience with carpentry, milling, metalworking, etc., well, good luck. You're going to need it.
[1] http://www.nationmaster.com/graph/eco_gdp_per_cap_in_195-eco...
[2] In 1913, 20% of the world's ships were built at Clyde.
[3] https://www.coursera.org/course/neuralnets
[4] About 1/3rd of the way through the course, he talks about a new technique that was published after the course actually started. The future of education is going to be awesome.