somu15
Bayesian inference, UQ for machine learning, Machine learning for UQ, Predictive models, Parallel algorithms for UQ/ML
Idaho National LaboratoryIdaho Falls, ID
Pinned Repositories
mastodon
A MOOSE app for structural dynamics, seismic analysis, and risk assessment.
moose
Multiphysics Object Oriented Simulation Environment
BIhNNs
The code enables to perform Bayesian inference in an efficient manner through the use of Hamiltonian Neural Networks (HNNs), Deep Neural Networks (DNNs), Neural ODEs, and Symplectic Neural Networks (SympNets) used with state-of-the-art sampling schemes like Hamiltonian Monte Carlo (HMC) and the No-U-Turn-Sampler (NUTS).
Bayesian_Ground_Motion_Selection
These are a set of codes for simulating the Conditional Spectrum using a Bayesian Analysis. Simulated ground motions can be conveniently combined with real ground motion data through these codes. For more information, please refer to "A Bayesian Treatment of the Conditional Spectrum Approach for Ground Motion Selection". Report by Somayajulu Dhulipala and Madeleine Flint.
Disf_Hazard
This repo consists of the codes used for a paper titled "DISFUNCTIONALITY HAZARD: A RISK-BASED TOOL TO SUPPORT THE RESILIENT DESIGN OF SYSTEMS SUBJECTED TO SINGLE HAZARDS AND MULTIHAZARDS."
Earthquake_Intensity_Measure_Sufficiency
These are the codes for IM selection paper.
GPmat
Matlab implementations of Gaussian processes and other machine learning tools.
hamiltonian-nn
Code for our paper "Hamiltonian Neural Networks"
Kernel_SeismicRisk
MAIN_Multihazard
Scripts for multihazard resilience assessment using semi-Markov processes non-renewal
somu15's Repositories
somu15/hamiltonian-nn
Code for our paper "Hamiltonian Neural Networks"
somu15/adnuts
An R package for NUTS sampling using ADMB
somu15/arviz
Exploratory analysis of Bayesian models with Python
somu15/awesome-neural-ode
A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.
somu15/BIhNNs
The code enables to perform Bayesian inference in an efficient manner through the use of Hamiltonian Neural Networks (HNNs) used with state-of-the-art sampling schemes like Hamiltonian Monte Carlo (HMC) and the No-U-Turn-Sampler (NUTS).
somu15/blackbear
BlackBear is a MOOSE-based code for simulating degradation processes in concrete and other structural materials.
somu15/Complex_systems_RNN
somu15/constrained-hamiltonian-neural-networks
somu15/deeponet
Learning nonlinear operators via DeepONet
somu15/deepxde
A library for scientific machine learning and physics-informed learning
somu15/diffusion
Denoising Diffusion Probabilistic Models
somu15/falcon
Fracturing And Liquid CONservation
somu15/gnn-powerflow
Graph Neural Network application in predicting AC Power Flow calculation. Developed with Pytorch Geometric framework. My Master Thesis at Eindhoven University of Technology
somu15/GraphNeuralSolver
somu15/IGAPack-PhaseField
Second and fourth-order adaptive phase field modeling of fracture using PHT-splines in the framework of IGA.
somu15/large_media
A repository for storing large images and movies associated with MOOSE documentation.
somu15/lightning
Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.
somu15/malamute
Advanced manufacturing modeling and simulation
somu15/mastodon
Mastodon is a MOOSE-based application for nonlinear, three-dimensional seismic soil-structure interaction analysis.
somu15/ML
somu15/modulus
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
somu15/moose
Multiphysics Object Oriented Simulation Environment
somu15/neml
Modular consitutive modeling library for structural materials
somu15/neuraluq
somu15/NUTS
python version of the No-U-Turn Sampler (NUTS) from Hoffman & Gelman, 2011
somu15/sfepy
Main SfePy repository
somu15/Small_Pf_code
somu15/somu15.github.io
Source code for website
somu15/sympnets
somu15/torchdiffeq
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.