Hacker News new | past | comments | ask | show | jobs | submit login

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




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: