DOE Patents title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Generative attribute optimization

Abstract

A generative attribute optimization (“GAO”) system facilitates understanding of effects of changes of attribute values of an object on a characteristic of the object and automatically identifying attribute values to achieve a desired result for the characteristic. The GAO system trains a generator (encoder and decoder) using an attribute generative adversarial network. The GAO model includes the trained generator and a separately trained predictor model. The GAO model inputs an input image and modified attribute values and employs the encoder and the decoder to generate a modified image that is the input image modified based on the modified attribute values. The GAO model then employs the predictor model to that inputs the modified image and generate a prediction of a characteristic of the modified image. The GAO system may employ an optimizer to modify the attribute values until an objective based on the desired result is achieved.

Inventors:
; ; ;
Issue Date:
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1925069
Patent Number(s):
11436427
Application Number:
16/807,006
Assignee:
Lawrence Livermore National Security, LLC (Livermore, CA)
Patent Classifications (CPCs):
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
DOE Contract Number:  
AC52-07NA27344
Resource Type:
Patent
Resource Relation:
Patent File Date: 03/02/2020
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Liu, Shusen, Han, Thomas, Kailkhura, Bhavya, and Loveland, Donald. Generative attribute optimization. United States: N. p., 2022. Web.
Liu, Shusen, Han, Thomas, Kailkhura, Bhavya, & Loveland, Donald. Generative attribute optimization. United States.
Liu, Shusen, Han, Thomas, Kailkhura, Bhavya, and Loveland, Donald. Tue . "Generative attribute optimization". United States. https://www.osti.gov/servlets/purl/1925069.
@article{osti_1925069,
title = {Generative attribute optimization},
author = {Liu, Shusen and Han, Thomas and Kailkhura, Bhavya and Loveland, Donald},
abstractNote = {A generative attribute optimization (“GAO”) system facilitates understanding of effects of changes of attribute values of an object on a characteristic of the object and automatically identifying attribute values to achieve a desired result for the characteristic. The GAO system trains a generator (encoder and decoder) using an attribute generative adversarial network. The GAO model includes the trained generator and a separately trained predictor model. The GAO model inputs an input image and modified attribute values and employs the encoder and the decoder to generate a modified image that is the input image modified based on the modified attribute values. The GAO model then employs the predictor model to that inputs the modified image and generate a prediction of a characteristic of the modified image. The GAO system may employ an optimizer to modify the attribute values until an objective based on the desired result is achieved.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2022},
month = {9}
}

Works referenced in this record:

Deep Learning Face Attributes in the Wild
conference, December 2015


"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
  • https://doi.org/10.1145/2939672.2939778

Gradient-based learning applied to document recognition
journal, January 1998


Visualizing and Understanding Convolutional Networks
book, January 2014


AttGAN: Facial Attribute Editing by Only Changing What You Want
journal, November 2019


Mimicking of corruption in images
patent-application, November 2020


Deep learning for computational biology
journal, July 2016


Feature Visualization
journal, November 2017


Causal inference in statistics: An overview
journal, January 2009


Searching for exotic particles in high-energy physics with deep learning
journal, July 2014


Materials discovery and design using machine learning
journal, September 2017


Generative machine learning systems for drug design
patent-application, June 2017


On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
journal, July 2015


Subset conditioning using variational autoencoder with a learnable tensor train induced prior
patent-application, March 2020


Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
conference, October 2017


Method and System for Unified Information Representation and Applications Thereof
patent-application, September 2012


Deep learning
journal, May 2015


Adversarial Examples: Attacks and Defenses for Deep Learning
journal, September 2019