Machine learning model explanation apparatus and methods
Abstract
Explanation apparatus and methods are described. In one aspect, an explanation apparatus includes processing circuity configured to access a source instance which has been classified by a machine learning model; create associations of the source instance with a plurality of training instances; and process the associations of the source instance and the training instances to identify a first subset of the training instances which have less relevance to the classification decision of the source instance by the machine learning model compared with a second subset of the training instances; and an interface configured to communicate information to a user, and wherein the processing circuitry is configured to control the user interface to communicate the second subset of the training instances to the user as evidence to explain the classification of the source instance by the machine learning model.
- Inventors:
- Issue Date:
- Research Org.:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 2293768
- Patent Number(s):
- 11797881
- Application Number:
- 16/555,530
- Assignee:
- Battelle Memorial Institute (Richland, WA)
- DOE Contract Number:
- AC05-76RL01830
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 08/29/2019
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Arendt, Dustin, and Huang, Zhuanyi. Machine learning model explanation apparatus and methods. United States: N. p., 2023.
Web.
Arendt, Dustin, & Huang, Zhuanyi. Machine learning model explanation apparatus and methods. United States.
Arendt, Dustin, and Huang, Zhuanyi. Tue .
"Machine learning model explanation apparatus and methods". United States. https://www.osti.gov/servlets/purl/2293768.
@article{osti_2293768,
title = {Machine learning model explanation apparatus and methods},
author = {Arendt, Dustin and Huang, Zhuanyi},
abstractNote = {Explanation apparatus and methods are described. In one aspect, an explanation apparatus includes processing circuity configured to access a source instance which has been classified by a machine learning model; create associations of the source instance with a plurality of training instances; and process the associations of the source instance and the training instances to identify a first subset of the training instances which have less relevance to the classification decision of the source instance by the machine learning model compared with a second subset of the training instances; and an interface configured to communicate information to a user, and wherein the processing circuitry is configured to control the user interface to communicate the second subset of the training instances to the user as evidence to explain the classification of the source instance by the machine learning model.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2023},
month = {10}
}
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Evaluation of Features for Leaf Discrimination
book, January 2013
- Silva, Pedro F. B.; Marçal, André R. S.; da Silva, Rubim M. Almeida
- Lecture Notes in Computer Science
Gene Selection for Cancer Classification using Support Vector Machines
journal, January 2002
- Guyon, Isabelle; Weston, Jason; Barnhill, Stephen
- Machine Learning, Vol. 46, Issue 1/3, p. 389-422
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
conference, January 2016
- Ribeiro, Marco Tulio; Singh, Sameer; Guestrin, Carlos
- Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16
Explainers for Machine Learning Classifiers
patent-application, February 2021
- Chatterjee, Bibaswan Kumar; Rao, Srinivasan Sengamedu Hanumantha
- US Patent Application 17/086073; 20210049512
Approximate nearest neighbors: towards removing the curse of dimensionality
conference, January 1998
- Indyk, Piotr; Motwani, Rajeev
- Proceedings of the thirtieth annual ACM symposium on Theory of computing - STOC '98
"What is relevant in a text document?": An interpretable machine learning approach
journal, August 2017
- Arras, Leila; Horn, Franziska; Montavon, Grégoire
- PLOS ONE, Vol. 12, Issue 8
The effects of example-based explanations in a machine learning interface
conference, March 2019
- Cai, Carrie J.; Jongejan, Jonas; Holbrook, Jess
- Proceedings of the 24th International Conference on Intelligent User Interfaces
Interacting with Predictions
conference, May 2016
- Krause, Josua; Perer, Adam; Ng, Kenney
- Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems
Extracting insights from the shape of complex data using topology
journal, February 2013
- Lum, P. Y.; Singh, G.; Lehman, A.
- Scientific Reports, Vol. 3, Issue 1
UMAP: Uniform Manifold Approximation and Projection
journal, September 2018
- McInnes, Leland; Healy, John; Saul, Nathaniel
- Journal of Open Source Software, Vol. 3, Issue 29
Intellingo
conference, April 2018
- Coppers, Sven; Van den Bergh, Jan; Luyten, Kris
- Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems
The role of trust in automation reliance
journal, June 2003
- Dzindolet, Mary T.; Peterson, Scott A.; Pomranky, Regina A.
- International Journal of Human-Computer Studies, Vol. 58, Issue 6
Nuclear feature extraction for breast tumor diagnosis
conference, July 1993
- Street, W. N.; Wolberg, W. H.; Mangasarian, O. L.
- SPIE Proceedings
Mitigating belief projection in explainable artificial intelligence via Bayesian teaching
journal, May 2021
- Yang, Scott Cheng-Hsin; Vong, Wai Keen; Sojitra, Ravi B.
- Scientific Reports, Vol. 11, Issue 1
Matplotlib: A 2D Graphics Environment
journal, January 2007
- Hunter, John D.
- Computing in Science & Engineering, Vol. 9, Issue 3
Characterizing the Role of Environment on Phenotypic Traits using Topological Data Analysis
conference, October 2016
- Kamruzzaman, Methun; Kalyanaraman, Ananth; Krishnamoorthy, Bala
- Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
Crush Your Data with ViC2ES Then CHISSL Away
conference, October 2018
- Arendt, Dustin L.; Franklin, Lyndsey R.; Yang, Fumeng
- 2018 IEEE Symposium on Visualization for Cyber Security (VizSec)
INFUSE: Interactive Feature Selection for Predictive Modeling of High Dimensional Data
journal, December 2014
- Krause, Josua; Perer, Adam; Bertini, Enrico
- IEEE Transactions on Visualization and Computer Graphics, Vol. 20, Issue 12
Interpreting Black-Box Classifiers Using Instance-Level Visual Explanations
conference, May 2017
- Tamagnini, Paolo; Krause, Josua; Dasgupta, Aritra
- Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics
Barcodes: The persistent topology of data
journal, October 2007
- Ghrist, Robert
- Bulletin of the American Mathematical Society, Vol. 45, Issue 01