Re:Create an algorithm to distinguish dogs from cats
by wojzaremba on Wednesday September 25, 2013 @02:41PM
(#6446437)
So far as it comes to large datasets unsupervised learning doesn't work ! You better off training initially discriminatively your network on imagenet, and then switch to this cat vs dog training. Rather, than do unsupervised learning.
Re:Create an algorithm to distinguish dogs from cats
by MrMan on Wednesday September 25, 2013 @04:05PM
(#6446947)
program it in Lush then.
everyone here found out about Deep Neural Networks and that is all they know.
Re:Create an algorithm to distinguish dogs from cats
by sharemywin on Wednesday September 25, 2013 @02:54PM
(#6446519)
Whole bunch of stuff on RBM and Deep belief nets. Also, has results on a competition on recognizing 1000 objects.
Pre deep belief network I'd agree with your guess on convolutional neural networks. However, now I'd guess you'd use a deep belief network to create a network that would pick out better features than those picked out "by hand" in the convolutional neural network. (See for example [1][2])
So my money would be on some deep belief network.
[1] Hinton, G. E, Osindero, S., and Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computation, 18:1527-1554.
[2] Building high-level features using large scale unsupervised learning arXiv:1112.6209