ProgramMaster Logo
Conference Tools for MS&T22: Materials Science & Technology
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting MS&T22: Materials Science & Technology
Symposium Uncertainty Quantification in Data-Driven Materials and Process Design
Presentation Title Learning from Multi-source Scarce Data via Latent Map Gaussian Processes
Author(s) Mehdi Shishehbor, Tammer Eweis-labolle, Ramin Bostanabad
On-Site Speaker (Planned) Ramin Bostanabad
Abstract Scope I will introduce latent map Gaussian processes (LMGPs) that inherit the attractive properties of GPs but are also applicable to mixed data that have both quantitative (e.g., pressure) and qualitative (e.g., coating type) inputs. I will elaborate on the core idea of LMGPs which consists of learning a low-dimensional manifold where all qualitative inputs are represented by some latent quantitative features. Through a wide range of analytical and real-world examples, I will demonstrate the advantages of LMGPs in terms of accuracy and versatility. I will show that LMGPs (1) can handle variable-length inputs, (2) have a nice neural network interpretation, and (3) dispense with manual featurization in Bayesian optimization. I will also demonstrate that LMGPs can fuse multiple sources of information together without imposing any hard constraints on how information sources, regardless of their fidelity level, should be fused or how the covariance of the errors is structured.

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Feature-rich Approach to the Characterization of High Temperature, Sulfate-induced Corrosion of Advanced Alloys
Active Learning for Density Functional Theory Simulations with DeepHyper
Anisotropic Creep Modeling and Uncertainty Quantification of an Electron Beam Melted AM Ni-Based Superalloy
Bayesian Calibrated Yield Strength Model for High-entropy Alloys
Bayesian Estimation and Active Learning of Data-driven Interatomic Potentials for Propagation of Uncertainty through Molecular Dynamics
Data-driven Modeling and Control for Temperature-controlled Shear Assisted Processing and Extrusion (ShAPE) using Koopman Operators
Data-driven Structure-property Mapping in Small Data Regime: Towards Increasing Generalizability
Efficient Phase Diagram Determination via Sequential Learning
Enabling the Fourth Paradigm of Multiscale ICME Models through Versatile Gaussian Process and Bayesian Optimization
Learning from Multi-source Scarce Data via Latent Map Gaussian Processes
Machine Learning of Phase Diagrams
Neural Network Surrogate Predictions with Uncertainties for Materials Science
Quantifying Uncertainty in Atomistic Exploration
Solving Stochastic Inverse Problems for Property–structure Linkages Using Data-consistent Inversion and Machine Learning
Thermodynamic Modeling with Uncertainty Quantification and its Implications for Intermetallic Catalysts Design: Application to Pd-Zn-Based Gamma-Brass Phase
Uncertainty Quantification of a High-throughput Local Plasticity Test: Profilometry-based Indentation Plastometry of Al 7075 T6 Alloy
Uncertainty Quantification of Constitutive Models in Crystal Plasticity Finite Element Method
Using Scalable Multi-Objective Bayesian Optimization to Develop Aluminum Scandium Nitride Molecular Dynamics Force Fields

Questions about ProgramMaster? Contact programming@programmaster.org