A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

A framework based on the tensor train decomposition for working with multivariate functions and multidimensional arrays

surrogate quantitative interpretability for deepnets

UQPyL is a python package for uncertainty quantification and parameter optimization. 参数不确定性分析及优化工具包。

Heron is a surrogate modelling toolkit for python, using Gaussian process regression.

Blackbox provides a standarized and efficient interface for evaluating variety of blackbox functions for various surrogate-based design activities

A novel neural network for effective learning of highly impulsive/oscillatory dynamic systems by jointly utilizing low-order derivatives

Mitigating the high computational costs associated with applying Bayesian model updating in inverse problems / Uncertainty Quantification and Efficient Sensitivity Analysis by using Surrogate Models

squid repository for manuscript analysis

This repository contains the packages that build the problem objects for the desdeo framework.

Tools for constructing a surrogate model for a stochastic numerical model using Probabilistic Learning on Manifolds in a small data context

Multi-Criteria Decision Making (MCDM) Framework for Building Energy Systems with Expedited Computation using Machine Learning (ML) Techniques

Learning Aerodynamics Through Data to Improve Optimization Algorithms

This repository contains scripts that were used for the experiments of our work named "Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling".

Surrogate modelling technique selectors

Hierarchical generative and regressive machine learning for next generation materials screening

Statistical learning models library for blackbox optimization

Trust-Region Filter/Funnel (TRF) solver is developed using the concepts from nonlinear optimisation, derivative-free optimisation and surrogate modelling, and is used to optimise grey box optimisation problems (coupling glass box mathematical models with available derivative information and the black box models without derivative information).

DL models for generating stress fields in microstructures

cNN-DP: Composite neural network with differential propagation for impulsive nonlinear dynamics.