A Caltech Library Service

Inverse Abstraction of Neural Networks Using Symbolic Interpolation

Dathathri, Sumanth and Gao, Sicun and Murray, Richard M. (2019) Inverse Abstraction of Neural Networks Using Symbolic Interpolation. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. Vol.33. Association for the Advancement of Artificial Intelligence (AAAI) , pp. 3437-3444. ISBN 978-1-57735-809-1.

[img] PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Neural networks in real-world applications have to satisfy critical properties such as safety and reliability. The analysis of such properties typically requires extracting information through computing pre-images of the network transformations, but it is well-known that explicit computation of pre-images is intractable. We introduce new methods for computing compact symbolic abstractions of pre-images by computing their overapproximations and underapproximations through all layers. The abstraction of pre-images enables formal analysis and knowledge extraction without affecting standard learning algorithms. We use inverse abstractions to automatically extract simple control laws and compact representations for pre-images corresponding to unsafe outputs. We illustrate that the extracted abstractions are interpretable and can be used for analyzing complex properties.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Murray, Richard M.0000-0002-5785-7481
Additional Information:© 2019 Association for the Advancement of Artificial Intelligence. The work is supported by DARPA Assured Autonomy, NSF CNS-1830399 and the VeHICaL project (NSF grant #1545126).
Group:Center for Autonomous Systems and Technologies (CAST)
Funding AgencyGrant Number
Defense Advanced Research Projects Agency (DARPA)UNSPECIFIED
Record Number:CaltechAUTHORS:20191003-134611922
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:99059
Deposited By: Tony Diaz
Deposited On:03 Oct 2019 21:23
Last Modified:16 Nov 2021 17:43

Repository Staff Only: item control page