Designing Neural Network Architectures using Reinforcement Learning · HackerPapers discussions

Designing Neural Network Architectures using Reinforcement Learning — mentioned by chriskanan

Fri, 14 Jul 2017 18:35:50 GMT

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

Paper and discussion history. A mention is not an endorsement.

Designing Neural Network Architectures using Reinforcement Learning — HN submission

Sun, 22 Jan 2017 11:45:35 GMT

Designing Neural Network Architectures Using Reinforcement Learning

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Designing Neural Network Architectures using Reinforcement Learning — mentioned by lucidrains

Tue, 03 Jan 2017 00:55:52 GMT

Other equally exciting papers that relates to learning to learn in DL. "Neural Architecture Search with Reinforcement Learning" https://arxiv.org/abs/1611.01578 "RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning" https://arxiv.org/abs/1611.02779 "Designing Neural Network Architectures using Reinforcement Learning" https://arxiv.org/abs/1611.02167

Paper and discussion history. A mention is not an endorsement.

Designing Neural Network Architectures using Reinforcement Learning — HN submission

Mon, 05 Dec 2016 09:25:25 GMT

Neural Networks Designed Using Reinforcement Learning

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Designing Neural Network Architectures using Reinforcement Learning — mentioned by lucidrains

Sat, 03 Dec 2016 21:33:54 GMT

absolutely dude.. for example, this paper just popped up in the last week https://arxiv.org/abs/1611.02167

Paper and discussion history. A mention is not an endorsement.