amiralizadeh1

function-estimation-correntropy

estimate a sine function using neural network by maximum correntropy criterion (MCC) and Mean Square Error (MSE) in a heavy-tailed noise (Cauchy and exponential) environment

PINNs

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

Channel-Parameter-Estimation-in-the-Presence-of-Phase-Noise-Based-on-Maximum-Correntropy-Criterion-

This project is a combination of information theory and machine learning in the application of signal processing at a receiver side corrupted by heavy-tailed noise distributions and AWGN

DeepXDE

My experiment with DeepXDE

KDE-vonmises

kernel density estimator (KDE) illustrates that the summation of Von Mises and Gaussian is heavy tailed

snippets

This is my back yard

test2

torchdiffeq

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.