<< Researchers have developed a flexible way of combining deep learning and symbolic reasoning to teach computers to write short computer programs. >>
<< A new program-writing AI, SketchAdapt, offers a way out. Trained on tens of thousands of program examples, SketchAdapt learns how to compose short, high-level programs, while letting a second set of algorithms find the right sub-programs to fill in the details. Unlike similar approaches for automated program-writing, SketchAdapt knows when to switch from statistical pattern-matching to a less efficient, but more versatile, symbolic reasoning mode to fill in the gaps. >>
<< Rather than rely on experts to define program structure, SketchAdapt figures it out using deep learning. The researchers also added a twist: When the neural networks are unsure of what code to place where, SketchAdapt is programmed to leave the spot blank for search algorithms to fill. >>
Kim Martineau. Toward artificial intelligence that learns to write code.
MIT. June17, 2019.
https://m.techxplore.com/news/2019-06-artificial-intelligence-code.html
Maxwell Nye, Luke Hewitt, et al. Learning to Infer Program Sketches.
arXiv:1902.06349v2 [cs.AI] Jun 4, 2019.