Geoffrey Hinton: Introduction to Deep Learning, Deep Belief Nets (2012) [video]

https://www.youtube.com/watch?v=GJdWESd543Y

by mindcrime • 11 years ago

61 5 11 years ago

youtube.com

hoaphumanoid• 11 years ago

His coursera lectures are awesome

king_magic• 11 years ago

This looks fantastic. Exactly the kind of intro for deep learning I've been looking for.

rudyl313• 11 years ago

Unfortunately this talk is kind of dated already. Most people don't stack RBMs or autoencoders to pretrain the weights anymore. If you use dropout with rectified linear units, you don't have to pretrain, even for large architectures.

bradneuberg2• 11 years ago

It's not just ReLUs that have helped, its also better random initialization before starting training, such as using Xavier initialization (http://andyljones.tumblr.com/post/110998971763/an-explanatio...)

Also, batch normalization helps with convergence as well. In addition, LSTMs work when dealing with recurrent neural nets.

bradneuberg2• 11 years ago

I completed this course over the last year. It's fantastic and from one of the founders of the field.

I'd stick to the first half to get a good sense of back propagation and working with standard neural nets. I'd hold off on the second half, which delve more into Restricted Boltzmann Machines (RBMs) or autoencoders; these aren't used as much anymore.

To augment your education for things that have happened since 2012, I'd learn about ReLUs rather than sigmoids for activation values, as well as studying up on convolutional neural networks (CNNs) and the recent work in sequence-to-sequence NLP translation via neural networks.

Geoffrey Hinton: Introduction to Deep Learning, Deep Belief Nets (2012) [video]

Related Stories