simonbing

discrepancy_vae

code for paper: Identifiability Guarantees for Causal Disentanglement from Soft Interventions

disentanglement_lib

disentanglement_lib is an open-source library for research on learning disentangled representations.

disentanglement_via_mechanism_sparsity

DVAE-speech

GP-VAE

TensorFlow implementation for the GP-VAE model described in https://arxiv.org/abs/1907.04155

HealthGen

HealthGen is a deep generative model to generate synthetic EHR time series with informative missing value patterns.

MIMIC_Extract

MIMIC-Extract:A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III

Multi-Node-CRL

PyTorch-GRU-D

PyTorch Implementation of GRU-D from "Recurrent Neural Networks for Multivariate Time Series with Missing Values" https://arxiv.org/abs/1606.01865

SCM

Generate data using a structural causal model

simonbing/SCM

Generate data using a structural causal model

simonbing/discrepancy_vae

code for paper: Identifiability Guarantees for Causal Disentanglement from Soft Interventions

simonbing/disentanglement_lib

disentanglement_lib is an open-source library for research on learning disentangled representations.

simonbing/disentanglement_via_mechanism_sparsity

simonbing/DVAE-speech

simonbing/GP-VAE

TensorFlow implementation for the GP-VAE model described in https://arxiv.org/abs/1907.04155

simonbing/HealthGen

HealthGen is a deep generative model to generate synthetic EHR time series with informative missing value patterns.

simonbing/MIMIC_Extract

MIMIC-Extract:A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III

simonbing/Multi-Node-CRL

simonbing/PyTorch-GRU-D

PyTorch Implementation of GRU-D from "Recurrent Neural Networks for Multivariate Time Series with Missing Values" https://arxiv.org/abs/1606.01865

simonbing/qmk_firmware

keyboard controller firmware for Atmel AVR and ARM USB families

simonbing/simonbing.github.io

Personal Page

simonbing/TimeGAN

Codebase for Time-series Generative Adversarial Networks (TimeGAN) - NeurIPS 2019