[jfv]

To be fair, reinforcement learning can be done with neural networks and can be seen as a form of "unsupervised learning". The results aren't as spectacular (yet?) as what we've seen in unsupervised learning, but it has potential.

I think the main problem is that we're incredibly dependent on advances in computing power to make advances in deep learning. IMHO, we've only made incremental software progress in using deep networks since the advent of convolutional networks.