Neural Network Verification is a Programming Language Challenge
This work addresses the need for better programming language support in neural network verification, which is incremental as it builds on existing verification efforts.
The paper argues that neural network verification should be treated as a programming language challenge, proposing this perspective to guide future solutions in the field.
Neural network verification is a new and rapidly developing field of research. So far, the main priority has been establishing efficient verification algorithms and tools, while proper support from the programming language perspective has been considered secondary or unimportant. Yet, there is mounting evidence that insights from the programming language community may make a difference in the future development of this domain. In this paper, we formulate neural network verification challenges as programming language challenges and suggest possible future solutions.