“By dividing up the labor - letting the neural nets handle the high-level structure, and using a search strategy to fill in the blanks - we can write efficient programs that give the right answer.” “Neural nets are pretty good at getting the structure right, but not the details,” says Armando Solar-Lezama, a professor at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL).
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. 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. No wonder it can be so frustrating.Ī new program-writing AI, SketchAdapt, offers a way out. Learning to code involves recognizing how to structure a program, and how to fill in every last detail correctly.
0 kommentar(er)
