Deep learning has transformed the way we think of software and what it can do. But deep neural networks are fragile and their behaviors are often surprising. In many settings, we need to provide formal guarantees on the safety, security, correctness, or robustness of neural networks. In this post, I will talk about the verification problem for neural networks and some of the prominent verification techniques that are being developed. I will also discuss the great challenges that our community is well positioned to address and some of the ideas that we can port from the machine-learning community.
This post discusses the task of automatic code completion through the application of deep learning methods.
The wealth of code now available on-line is fertile ground to enable machine learning to be applied to programming tasks. This post is the second in a series on this topic, focusing on the tasks of semantically labeling and captioning code.
The wealth of code now available on-line is fertile ground to enable machine learning to be applied to programming tasks. This post discusses the promise of and some progress on the problem “deep code.” It is the first in a series.