In a new paper, Self-Supervised Bug Detection and Repair, presented at the 2021 Conference on Neural Information Processing Systems (NeurIPS 2021), Microsoft show a promising deep learning model, called BugLab.
BugLab can be taught to detect and fix bugs, without using labelled data, through a “hide and seek” game. The goal of our work is to develop better AI that can automatically find and repair bugs.
BugLab uses two competing models that learn by playing a “hide and seek” game that is broadly inspired by generative adversarial networks (GAN).
For some samples, please check out the Microsoft blog at the link below.
Links:
- https://www.microsoft.com/en-us/research/blog/finding-and-fixing-bugs-with-deep-learning/