Interpreting neural network judgments via minimal, stable, and symbolic corrections

Interpreting neural network judgments via minimal, stable, and symbolic corrections

© 2018 Curran Associates Inc..All rights reserved. We present a new algorithm to generate minimal, stable, and symbolic corrections to an input that will cause a neural network with ReLU activations to change its output. We argue that such a correction is a useful way to provide feedback to a user w...

Full description

Bibliographic Details
Main Authors: Solar Lezama, Armando, Singh, Rishabh, Zhang, Xin
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format: Article
Language:English
Published: 2021
Online Access:https://hdl.handle.net/1721.1/137906

Internet

https://hdl.handle.net/1721.1/137906

Similar Items