Neural Architecture Search with Reinforcement Learning

Re:Neural Architecture Search with Reinforcement Learning by jorgemf on Thursday January 19, 2017 @06:06PM (#13440314)

I would love to see a Neural Architecture Search that create Neural Architecture Search as a future research project. Meta-meta-learning. I like the idea of improving the network which creates other networks.

Also the size of the network can be used as part of the evaluation in order to minimize the networks and maximize the accuracy.

[ Parent | on HN ]

Re:Neural Architecture Search with Reinforcement Learning by westoncb on Thursday January 19, 2017 @07:25PM (#13440748)

I would guess the computational complexity involved in training the top level network would make the project infeasible.

[ Parent | on HN ]

Re:Neural Architecture Search with Reinforcement Learning by jorgemf on Thursday January 19, 2017 @09:04PM (#13441216)

You can relax the problem in order to reduce complexity and calculations. For example: cut the training of slow learning networks, have a database of already trained networks, decrease the number of epochs and examples, etc. Or even create another network which predicts the convergence of a network and use it as heuristic. If you also take into account the size of the network and force the learning to minimize them, then you can train them faster.

We cannot do it at home, but for sure Google can try it in their servers.

[ Parent | on HN ]