News for hackers. Stuff that matters.
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by pigscantfly on Thursday May 21, 2015 @09:24PM (#9586234)
Andrej is also a great lecturer; his CS231n class in the winter was both the most enjoyable and educational I've taken all year. All of the materials are available at cs231n.stanford.edu, although I can't seem to find the lecture videos online. It may not have been recorded.

As a bonus, there's an ongoing class on deep learning architectures for NLP which covers Recurrent (and Recursive) Neural nets in depth (as well as LSTM's and GRU's). Check out cs224d.stanford.edu for lecture notes and materials. The lectures are definitely being recorded, but I don't think they're publicly available yet.

Re:The Unreasonable Effectiveness of Recurrent Neural Networks by outdated on Friday May 22, 2015 @02:12AM (#9586756)
Yay, looks like the videos for cs224d are available on http://cs224d.stanford.edu/syllabus.html
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by octatoan on Friday May 22, 2015 @07:10AM (#9587619)
He's good at demystifying a lot of things. He's taught thousands (at least) of people how to get started with solving the Rubik's cube competitively (shortest-time) via his YouTube channel.

His username is badmephisto if you're interested.

Re:The Unreasonable Effectiveness of Recurrent Neural Networks by wonderingwhere on Friday May 22, 2015 @05:18PM (#9590931)
The tree that just gives and gives! Thank you!
Re:The Unreasonable Effectiveness of Recurrent Neural Networks by tim333 on Friday May 22, 2015 @09:53AM (#9588245)
It's cool having the network running live in your browser on the cs231n.stanford.edu page