Browse wiki

From MurrayWiki
Jump to: navigation, search
Inverse Abstraction of Neural Networks Using Symbolic Interpolation
Abstract Neural networks in real-world applications …
Neural networks in real-world applications have to satisfy critical properties such as safety and reliability. The analysis of such properties typically involves extracting informa- tion through computing pre-images of neural networks, 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. Our approach relies on computing approximations that provably overapproximate and underapproximate the pre-images at all layers. The abstraction of pre-images enables formal analysis and knowl- edge extraction without modifying standard learning algo- rithms. We show how to 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 often interpretable and can be used for analyzing complex properties.
be used for analyzing complex properties.  +
Authors Sumanth Dathathri, Sicun Gao, Richard M. Murray  +
Funding VeHICaL: Verified Human Interfaces, Control, and Learning for Semi-Autonomous Systems +
ID 2018e  +
Source To appear, 2019 AAAI Conference on Artificial Intelligence  +
Tag dgm19-aiaa  +
Title Inverse Abstraction of Neural Networks Using Symbolic Interpolation +
Type Conference paper  +
Categories Papers
Modification date
This property is a special property in this wiki.
27 December 2018 05:21:34  +
URL
This property is a special property in this wiki.
http://www.cds.caltech.edu/~murray/preprints/dgm19-aiaa.pdf  +
hide properties that link here 
Inverse Abstraction of Neural Networks Using Symbolic Interpolation + Title
 

 

Enter the name of the page to start browsing from.