Trust-Enhancing Probabilistic Transfer Learning for Sparse and Noisy Data Environments
- Sandia National Lab. (SNL-CA), Livermore, CA (United States)
- Meta, Menlo Park, CA (United States)
- Stanford Univ., CA (United States)
There is an increasing aspiration to utilize machine learning (ML) for various tasks of relevance to national security. ML models have thus far been mostly applied to tasks and domains that, while impactful, have sufficient volume of data. For predictive tasks of national security relevance, ML models of great capacity (ability to approximate nonlinear trends in input-output maps) are often needed to capture the complex underlying physics. However, scientific problems of relevance to national security are often accompanied by various sources of sparse and/or incomplete data, including experiments and simulations, across different regimes of operation, of varying degrees of fidelity, and include noise with different characteristics and/or intensity. State-of-the-art ML models, despite exhibiting superior performance on the task and domain they were trained on, may suffer detrimental loss in performance in such sparse data environments. This report summarizes the results of the Laboratory Directed Research and Development project entitled Trust-Enhancing Probabilistic Transfer Learning for Sparse and Noisy Data Environments. The objective of the project was to develop a new transfer learning (TL) framework that aims to adaptively blend the data across different sources in tackling one task of interest, resulting in enhanced trustworthiness of ML models for mission- and safety-critical systems. The proposed framework determines when it is worth applying TL and how much knowledge is to be transferred, despite uncontrollable uncertainties. The framework accomplishes this by leveraging concepts and techniques from the fields of Bayesian inverse modeling and uncertainty quantification, relying on strong mathematical foundations of probability and measure theories to devise new uncertainty-aware TL workflows.
- Research Organization:
- Sandia National Laboratories (SNL-CA), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program
- DOE Contract Number:
- NA0003525
- OSTI ID:
- 2430286
- Report Number(s):
- SAND--2023-10257R
- Country of Publication:
- United States
- Language:
- English
Similar Records
A Study on Efficient Reinforcement Learning Through Knowledge Transfer
Multi-Kernel Adaptive Support Vector Machine for Scalable Predictive Maintenance
Journal Article
·
Fri Sep 30 20:00:00 EDT 2022
· Federated and Transfer Learning Adaptation, Learning, and Optimization
·
OSTI ID:1987999
Multi-Kernel Adaptive Support Vector Machine for Scalable Predictive Maintenance
Conference
·
Mon Oct 31 20:00:00 EDT 2022
·
OSTI ID:1891921