Neel Kant
2018 · arXiv
In recent years, deep learning has made tremendous progress in a number of fields that were previously out of reach for artificial intelligence. The successes in these problems has led researchers to consider the possibilities for intelligent systems to tackle a problem that humans have only recently themselves considered: program synthesis. This challenge is unlike others such as object recognition and speech translation, since its abstract nature and demand for rigor make it difficult even for human minds to attempt. While it is still far from being solved or even competitive with most existing methods, neural program synthesis is a rapidly growing discipline which holds great promise if completely realized. In this paper, we start with exploring the problem statement and challenges of program synthesis. Then, we examine the fascinating evolution of program induction models, along with how they have succeeded, failed and been reimagined since. Finally, we conclude with a contrastive look at program synthesis and future research recommendations for the field.
Metadata: arXiv. Abstracts retain their original authors’ rights.
Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels
3 selected excerpts · 3 total mentions
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...
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.
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
More from the same topics.
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition.
Tom B. Brown, Benjamin Mann, Nick Ryder +28
Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task.
Chiyuan Zhang, Samy Bengio, Moritz Hardt +2
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance.
A. Pluchino. A. E. Biondo, A. Rapisarda
The largely dominant meritocratic paradigm of highly competitive Western cultures is rooted on the belief that success is due mainly, if not exclusively, to personal qualities such as talent, intelligence, skills, efforts or risk taking.