The increasing use of deep neural networks (DNNs) in a variety of applications, including some safety-critical ones, has brought renewed interest in the topic of verification of neural networks. However, verification is only meaningful when paired with high-quality formal specifications. In this note, we survey the landscape of formal specification for deep neural networks. Our goal is to lay an initial foundation for formalizing and reasoning about properties of DNNs, and for using these properties in a rigorous design and verification methodology.
Formal Specification for Deep Neural Networks
Researchers may make free and open use of the UC Berkeley Library’s digitized public domain materials. However, some materials in our online collections may be protected by U.S. copyright law (Title 17, U.S.C.). Use or reproduction of materials protected by copyright beyond that allowed by fair use (Title 17, U.S.C. § 107) requires permission from the copyright owners. The use or reproduction of some materials may also be restricted by terms of University of California gift or purchase agreements, privacy and publicity rights, or trademark law. Responsibility for determining rights status and permissibility of any use or reproduction rests exclusively with the researcher. To learn more or make inquiries, please see our permissions policies (https://www.lib.berkeley.edu/about/permissions-policies).