Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

On Transfer Learning Of Neural Networks Using Bi-Fidelity Data For Uncertainty Propagation

Journal Article · · International Journal for Uncertainty Quantification
 [1];  [2];  [3];  [1];  [1];  [1]
  1. Univ. of Colorado, Boulder, CO (United States)
  2. Univ. of California, Riverside, CA (United States)
  3. National Renewable Energy Lab. (NREL), Golden, CO (United States)

Due to their high degree of expressiveness, neural networks have recently been used as surrogate models for mapping inputs of an engineering system to outputs of interest. Once trained, neural networks are computationally inexpensive to evaluate and remove the need for repeated evaluations of computationally expensive models in uncertainty quantification applications. However, given the highly parameterized construction of neural networks, especially deep neural networks, accurate training often requires large amounts of simulation data that may not be available in the case of computationally expensive systems. In this paper, to alleviate this issue for uncertainty propagation, we explore the application of transfer learning techniques using training data generated from both high- and low-fidelity models. We explore two strategies for coupling these two datasets during the training procedure, namely, the standard transfer learning and the bi-fidelity-weighted learning. In the former approach, a neural network model mapping the inputs to the outputs of interest is trained based on the low-fidelity data. The high-fidelity data are then used to adapt the parameters of the upper layer(s) of the low-fidelity network, or train a simpler neural network to map the output of the low-fidelity network to that of the high-fidelity model. In the latter approach, the entire low-fidelity network parameters are updated using data generated via a Gaussian process model trained with a small high-fidelity dataset. The parameter updates are performed via a variant of stochastic gradient descent with learning rates given by the Gaussian process model. Using three numerical examples, we illustrate the utility of these bi-fidelity transfer learning methods where we focus on accuracy improvement achieved by transfer learning over standard training approaches.

Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Sponsoring Organization:
USDOE; Defense Advanced Research Projects Agency (DARPA); National Science Foundation (NSF)
Grant/Contract Number:
AC36-08GO28308
OSTI ID:
1769854
Report Number(s):
NREL/JA--2C00-75670; MainId:6900; UUID:cb9e8f5e-3920-ea11-9c2a-ac162d87dfe5; MainAdminID:19830
Journal Information:
International Journal for Uncertainty Quantification, Journal Name: International Journal for Uncertainty Quantification Journal Issue: 6 Vol. 10; ISSN 2152-5080
Publisher:
Begell HouseCopyright Statement
Country of Publication:
United States
Language:
English

References (13)

Porous-electrode theory with battery applications journal January 1975
Approximation by superpositions of a sigmoidal function journal December 1989
Combining multiple surrogate models to accelerate failure probability estimation with expensive high-fidelity models journal July 2017
A new learning paradigm: Learning using privileged information journal July 2009
Turbulence and the dynamics of coherent structures. I. Coherent structures journal January 1987
Accurate Uncertainty Quantification Using Inaccurate Computational Models journal January 2009
Knowledge transfer via classification rules using functional mapping for integrative modeling of gene expression data journal July 2015
Recursive Co-Kriging Model for Design of Computer Experiments with Multiple Levels of Fidelity journal January 2014
A one-equation turbulence model for aerodynamic flows conference February 2013
Transfer Learning book January 2010
Parameter tuning for a multi-fidelity dynamical model of the magnetosphere text January 2013
On Uncertainty Quantification of Lithium-ion Batteries: Application to an LiC$_6$/LiCoO$_2$ cell preprint January 2015
Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations text January 2017

Cited By (2)


Similar Records

Transfer learning of neural surrogates on multifidelity groundwater simulations
Dataset · Tue Dec 31 23:00:00 EST 2024 · OSTI ID:3005558

Data-driven wind turbine wake modeling via probabilistic machine learning
Journal Article · Fri Apr 01 00:00:00 EDT 2022 · Neural Computing and Applications · OSTI ID:1890486

Data-driven wind turbine wake modeling via probabilistic machine learning
Journal Article · Mon Jan 10 23:00:00 EST 2022 · Neural Computing and Applications · OSTI ID:1884972