On the Practical Computational Power of Finite Precision RNNs for Language Recognition — mentioned by YeGoblynQueenne

Mon, 18 Nov 2019 10:36:00 GMT

Neural nets can still not solve aⁿbⁿ. This is the latest attempt of which I'm aware: On the Practical Computational Power of Finite Precision RNNs for Language Recognition https://arxiv.org/abs/1805.04908 Typically, it claims generalisation but fails to demonstrate it. As we agreed, it's a simple problem. Neural nets can't solve it. Do you understand why? Re: classification, AlphaZero is a great example of what I'm talking about. The game-playing logic is provided by MCTS, a GOFAI algorithm (it's a variant of good, old minimax). The neural net component is only used to identify promising…

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

On the Practical Computational Power of Finite Precision RNNs for Language Recognition — mentioned by canjobear

Fri, 24 Aug 2018 20:55:33 GMT

LSTMs can learn a count mechanism that lets them recognize a^n b^n and a^n b^n c^n: https://arxiv.org/pdf/1805.04908.pdf

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

On the Practical Computational Power of Finite Precision RNNs for Language Recognition · HackerPapers discussions

On the Practical Computational Power of Finite Precision RNNs for Language Recognition — mentioned by YeGoblynQueenne

On the Practical Computational Power of Finite Precision RNNs for Language Recognition — mentioned by canjobear