RE: Supermathematics and Artificial General Intelligence
September 8, 2017 at 2:56 am
(This post was last modified: September 8, 2017 at 3:00 am by causal code.
Edit Reason: Added cool links
)
I always wondered how they would solve reinforcement learning time-dependency problems, because RL had some issues with time dependent games.
But, it looks like "manifold learning" allows for deep learning models to "generalize across time", which is cool.
Some interesting papers:
"VAE" networks, for computation wrt to features like position across time:
https://arxiv.org/abs/1606.05579
Improving the long term temporal dependency of recurrent networks:
https://deepmind.com/blog/decoupled-neur...gradients/
But, it looks like "manifold learning" allows for deep learning models to "generalize across time", which is cool.
Some interesting papers:
"VAE" networks, for computation wrt to features like position across time:
https://arxiv.org/abs/1606.05579
Improving the long term temporal dependency of recurrent networks:
https://deepmind.com/blog/decoupled-neur...gradients/