Learning to Execute · HackerPapers discussions

Learning to Execute — mentioned by shriphani

Sat, 03 Jun 2017 05:24:01 GMT

There was similar work by W. Zaremba (OpenAI I think). LSTM trained to interpret python source code. Took a ton of hackery to get it to not fall apart on simple operations and it continued making indexing errors. I wouldn't read too much into these results. https://arxiv.org/abs/1410.4615

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

Learning to Execute — mentioned by sapphireblue

Fri, 22 Jul 2016 20:12:54 GMT

There are signs, if you know were to look for them: http://arxiv.org/abs/1510.07211 https://arxiv.org/abs/1410.4615 http://arxiv.org/abs/1605.06640 https://arxiv.org/abs/1410.5401

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

Learning to Execute — mentioned by Smerity

Tue, 23 Jun 2015 06:30:13 GMT

Whilst you are correct that the number of allowed computation steps is limited, LSTMs have still been used with success for such tasks. LSTMs have been used to perform addition with 99% accuracy^ on two 9-digit numbers[1]. The paper even shows that simple Python programs can be evaluated with some degree of accuracy. Remember that even if the number of computation steps is limited, there can be multiple layers ([1] uses 2) and each neuron unit can perform a computation ([1] uses 400 cells per layer). It only needs to learn how to be an ALU. The work is in fact done by one of the people who…

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

Learning to Execute — 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.

Learning to Execute — mentioned by pasbesoin

Sat, 29 Nov 2014 18:25:20 GMT

No big criticism implied, but some of us like to see the abstract, first. So here's the link to it: http://arxiv.org/abs/1410.4615

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

Learning to Execute — HN submission

Sat, 29 Nov 2014 11:09:27 GMT

Learning to Execute [pdf]

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

Learning to Execute — mentioned by modeless

Sat, 01 Nov 2014 22:46:58 GMT

> has built some impressive predictive systems Do you have any links to examples? I'm not aware of any systems built with HTMs that I'd consider "impressive" relative to what ANNs are doing these days, e.g. learning to play Atari games by watching the screen [1], approaching human performance on object classification in unrestricted images [2], or learning to execute simple python programs by reading the source code [3]. [1] https://medium.com/the-physics-arxiv-blog/the-last-ai-breakt... [2] http://karpathy.github.io/2014/09/02/what-i-learned-from-com... [3] http://arxiv.org/abs/1410.4615

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

Learning to Execute — HN submission

Tue, 28 Oct 2014 03:03:38 GMT

Learning to Execute

42 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Learning to Execute — mentioned by javierluraschi

Sun, 26 Oct 2014 22:24:13 GMT

http://arxiv.org/pdf/1410.4615v1.pdf

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