In short, this architecture freezes the parameters and pathways used for previously learned tasks, and can learn new parameters and use new pathways for new tasks, with each new task learned faster than previous ones by leveraging all previously learned parameters and pathways (more efficient transfer learning).
"During learning, a tournament selection genetic algorithm is used to select pathways through the neural network for replication and mutation."
Trying to think of another 'tournament' like process that would allow for a massive distributed network where each node already has a decent GPU, where something like this could be successfully run. Maybe someone could help me out here...
I assume you're being sarcastic; they do point out in the intro and at the end that a deep RL agent could be trained to do the topology selections, but that would be more work to get going than some simple evolutionary operators, and is left to future work. Don't worry, I'm sure it'll be A3C all the way down eventually...
cs702|9 years ago
It's a general neural net architecture.
Very cool.
divbit|9 years ago
Trying to think of another 'tournament' like process that would allow for a massive distributed network where each node already has a decent GPU, where something like this could be successfully run. Maybe someone could help me out here...
gwern|9 years ago