Hacker News Reader

Note: This is about unsupervised learning and mostly about RBMs/DBNs. Most of the Deep Learning success is all about supervised learning. In the past, RBMs have been used for unsupervised pretraining of the model, however, nowadays, everyone uses supervised pretraining.

And the famous DeepMind works (Atari games etc) is mostly about Reinforcement learning, which is again different.

View on HN

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.

Well, if I understood correctly, the RL DeepMind implementation is basically making a RL algorithm work with a supervised model.

This has been done since the 90s. The Deepmind paper is about a few more tricks.

Reply on news.ycombinator.com