Dilan Kilic's starred repositories
deep-learning-with-python-notebooks
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
PINNpapers
Must-read Papers on Physics-Informed Neural Networks.
machine-learning-exams
This repository contains links to machine learning exams, homework assignments, and exercises that can help you test your understanding.
pde-surrogate
Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
Deep-Learning-Based-Structural-Damage-Detection
Structural damage detection using convolutional neural networks
PoreFlow-Net
3D CNN to predict single-phase flow velocity fields
CNN-for-Airfoil
CNN for airfoil lift-to-drag-ratio prediction
Deep-Learning-for-Aerodynamic-Prediction
This repository contains code used to create and train a deep neural network that replicates a RANS solver for aerodynamic prediction over airfoils.
AeroelasticAirfoil-SU2
A simple framework that automatically generates SU2 configuration (.cfg) files and make calls to SU2 to perform aeroelastic simulations all within Python. The Matrix Pencil method is then used to compute the damping coefficient.
1d-pinn-reconstruction
This is the code for "Neural Network Reconstruction of Plasma Space-Time" by C.Bard and J.Dorelli (DOI: 10.3389/fspas.2021.732275). It is a Physics-Informed Transformer Neural Network which was used to reconstruct one-dimensional (M)HD shocktubes from partial samples. Includes source code, data, and jupyter notebooks for scientific reproduction
Picewise-linear-Rayleigh-Ritz
I use piecewise linear function to approximate the solution to a boundary value problem.
IH-GAN_CMAME_2022
IH-GAN, data generation, and topology optimization code associated with our accepted CMAME 2022 paper: "IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures."
structure_vibration
code for lecture
Physics_informed_GANs_turbulent_flows
Generative Adversarial Networks are used to super resolve turbulent flow fields from low resolution (RANS/LES) fields to high resolution (DNS) fields without solving NS equations numerically.
ml-cfd-lecture
Lecture material for machine learning applied to computational fluid mechanics
ModalPINN_Python_code
Publication of Python code used to train ModalPINN
PyTorch-GAN
PyTorch implementations of Generative Adversarial Networks.
awesome-gan-for-medical-imaging
Awesome GAN for Medical Imaging