Reinforcement Learning Neural Turing Machines - Revised · HackerPapers discussions

Reinforcement Learning Neural Turing Machines - Revised — mentioned by GregarianChild

Wed, 21 Oct 2020 21:19:38 GMT

Reinforcement learning is Turing complete [1], so if AI is possible at all, then it can be realised through RL. cognitive psychology You are overselling the insights of this discipline. Has cognitive psychology solved its replication problems? Where is the world-beating AI that is based on "concept spaces", "sparse representations", "small-world networks" and "learning and memory" neuroscience? [1] https://arxiv.org/abs/1505.00521

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

Reinforcement Learning Neural Turing Machines - Revised — mentioned by visarga

Sun, 22 May 2016 09:11:40 GMT

It's very experimental. The great thing about them is that they open the possibility of building new types of interfaces like memory, stack, tape, database or search engine that work with neural networks in inference. See https://arxiv.org/pdf/1505.00521v3.pdf

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

Reinforcement Learning Neural Turing Machines - Revised — HN submission

Wed, 17 Jun 2015 02:03:39 GMT

Reinforcement Learning Neural Turing Machines

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

Reinforcement Learning Neural Turing Machines - Revised — mentioned by deepnet

Sun, 24 May 2015 08:43:55 GMT

In "Learning to Execute" by Zaremba & Sutskever http://arxiv.org/abs/1410.4615 An RNN learns snippets of python Their next paper is "Reinforcement Learning Neural Turing Machines" http://arxiv.org/abs/1505.00521 based on Graves "Neural Turing Machines" http://arxiv.org/abs/1410.5401, which attempts to infer algorithms from the result. In a lost BBC interview from 1951 Turing reputedly spoke of evolving cpu bitmasks for computation.

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

Reinforcement Learning Neural Turing Machines - Revised — HN submission

Tue, 05 May 2015 20:08:37 GMT

Reinforcement Learning Neural Turing Machines

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