bearzoo

They are doing nothing but starting with random noise, and then learning a representation of an image that will maximize the probability in the output layer (by suggesting to the network that this noise should have actually been recognized as a banana or what have you) and back propagating changes into the input layer. Essentially, this has been happening since 2003 in the natural language processing world where we learn 'distributed representations' of words by starting with random representations of words, and learning them by context by back propagating changes into the input layer. Very cool though.

^agreed - no ANN can be treated as a 'jack of all trades' because of the success found in one domain (it seems more networks are designed to boost performance on one type of data)

'Deep learning' is the new 'big data'

From reading the abstract it seems that they are claiming that introducing some randomness into your gradient of weight changes allows for the quicker convergence of solution - I did not read the paper. I also don't exactly understand why it works - it sounds like they are claiming traditional back prop has room for improvement.

The brain has no objective function it is trying to minimize

oh the power of buzzwords