Recent Advances in Neural Program Synthesis · HackerPapers discussions

Recent Advances in Neural Program Synthesis — mentioned by exdsq

Thu, 16 Jan 2020 12:03:42 GMT

This problem is being worked on but it is by no means solved! This paper [0] is a pretty decent survey on the field and [1] is an excellent article on the topic at a high level, written by a team currently working in the space (synthesising smart contracts). [0] https://arxiv.org/pdf/1802.02353.pdf [1] https://medium.com/@vidiborskiy/software-writes-software-pro...

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

Recent Advances in Neural Program Synthesis — mentioned by painful

Fri, 01 Mar 2019 16:38:45 GMT

I would not write it at all. Instead, I would write only the test cases, thereby documenting the requirements. I would then evolve the software using modern machine learning techniques which are capable of program synthesis: https://arxiv.org/abs/1802.02353 The underlying implementation can keep changing but the requirements and tests don't change so much.

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

Recent Advances in Neural Program Synthesis — mentioned by tree_of_item

Sat, 29 Sep 2018 19:38:27 GMT

Yes, you will want to research "program induction" and "program synthesis". For a review of recent work in both, see https://arxiv.org/abs/1802.02353 For program synthesis applied to the "Atari" deep learning benchmark check out https://arxiv.org/abs/1806.05695

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

Recent Advances in Neural Program Synthesis — HN submission

Sat, 10 Feb 2018 03:44:23 GMT

Recent Advances in Neural Program Synthesis

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