Czqstrong

en_flows

vae-lagging-encoder

PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

variational-autoencoder

Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)

variational-autoencoder

generate MNIST using a Variational Autoencoder

machine-learning-notes

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (1000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(1000+页)和视频链接

Kernel-Density-Estimation-with-Linked-BCs

Code for paper (with same title).

randomforest-density-python

Random Forests for Density Estimation in Python

wan

A deep learning based method for solving high dimensional partial differential equations based on its weak form

PDPINN

DGM

Deep Galerkin Method

DeepRitzMethod

Group project for Deep Learning: Algorithms and Applications in Peking University 2018 Spring. This is a brief survey, discussion and implementation for deep Ritz method.

getdist

MCMC sample analysis, kernel densities, plotting, and GUI

Mixture-Density-Networks-for-distribution-and-uncertainty-estimation

A generic Mixture Density Networks (MDN) implementation for distribution and uncertainty estimation by using Keras (TensorFlow)

pytorch-flows

PyTorch implementations of algorithms for density estimation

nndl.github.io

《神经网络与深度学习》 邱锡鹏著 Neural Network and Deep Learning

kalepy

Kernel Density Estimation and (re)sampling

kernel-density

Multivariate kernel density estimation [statistics]

NN_Theory_Tester

bandwidth-selection-CFM

Code to evaluate LSCV errors for Conditional Frontier Models

kernel_regression

Implementation of Nadaraya-Watson kernel regression with automatic bandwidth selection compatible with sklearn.

least-squares-cross-validation-in-KDE

This code is to compute the optimal bandwidth based the lscv criteria in kernel density estimation

deepxde

A library for scientific machine learning and physics-informed learning

PINNs-TF2.0

TensorFlow 2.0 implementation of Maziar Raissi's Physics Informed Neural Networks (PINNs).

PINNs

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

awesome-deep-learning-papers

The most cited deep learning papers

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

PDE-Net

PDE-Net: Learning PDEs from Data

DeepHPMs

Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations

data-driven-advection