Re:Why Deep Learning Works II: the Renormalization Group
by charleshmartin on Sunday July 05, 2015 @03:12PM
(#9834565)
I will address the supervised vs unsupervised issue in my next post. Here, I believe the analogy would be that when a field is applied to a spin glass, it does not exhibit a glass transition to a non-self-averaging (highly non-convex) ground state.
As to supervised vs reinforcement learning, its not that different. See how Vowpal Wabbit incoporates both the 2 ideas in how the SGD update is formulated.
Re:Why Deep Learning Works II: the Renormalization Group
by BenderV on Sunday July 05, 2015 @12:22PM
(#9833984)
Well, if I understood correctly, the RL DeepMind implementation is basically making a RL algorithm work with a supervised model.
Re:Why Deep Learning Works II: the Renormalization Group
by sieisteinmodel on Sunday July 05, 2015 @01:52PM
(#9834262)
This has been done since the 90s. The Deepmind paper is about a few more tricks.
And the famous DeepMind works (Atari games etc) is mostly about Reinforcement learning, which is again different.