Re:Hacker's guide to Neural Networks (2012)
by nomel on Friday July 14, 2017 @02:14PM
(#14771968)
I know nothing about any of this, but has there been any work into using neural networks to guide and vary the parameter values during training?
[ Parent
| on HN ]
Re:Hacker's guide to Neural Networks (2012)
by chriskanan on Friday July 14, 2017 @02:35PM
(#14772160)
There has been some work related to what you are describing:
Learning to learn by gradient descent by gradient descent https://arxiv.org/abs/1606.04474
Related (but less so), there are also some papers about learning neural network architectures:
Designing Neural Network Architectures using Reinforcement Learning https://arxiv.org/abs/1611.02167
Neural Architecture Search with Reinforcement Learning https://arxiv.org/abs/1611.01578