Interpreting neural network judgments via minimal, stable, and symbolic corrections
Name
7736-interpreting-neural-network-judgments-via-minimal-stable-and-symbolic-corrections.pdf
Description
Published version
Size
3.68 MB
Format
Adobe PDF
Checksum (MD5)
31307a16376bea99cdeaff0bdd52a413
Author(s)
Solar Lezama, Armando
Singh, Rishabh
Zhang, Xin
Date Issued
2018
Citation
Solar Lezama, Armando, Singh, Rishabh and Zhang, Xin. 2018. "Interpreting neural network judgments via minimal, stable, and symbolic corrections."
Version
Final published version
Abstract
© 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 when the network's output is different from a desired output. Our algorithm generates such a correction by solving a series of linear constraint satisfaction problems. The technique is evaluated on three neural network models: one predicting whether an applicant will pay a mortgage, one predicting whether a first-order theorem can be proved efficiently by a solver using certain heuristics, and the final one judging whether a drawing is an accurate rendition of a canonical drawing of a cat.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/7736-interpreting-neural-network-judgments-via-minimal-stable-and-symbolic-corrections
