Re:Towards deep symbolic reinforcement learning
by jesuslop on Saturday October 15, 2016 @07:31PM
(#12716118)
In addition to the intro that I liked a lot, I find interesting, or even important, the usage of an unsupervised method to generate the visual symbolic dictionary, a convolutional autoencoder here.
In arxiv:1412.6856 unsupervised object detectors emerge as byproducts in a CNN for another kind of task, for more interesting, photorealistic objects.
In arxiv:1412.6856 unsupervised object detectors emerge as byproducts in a CNN for another kind of task, for more interesting, photorealistic objects.