SR CNN VAE GAN

Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation

Features

Data Augmentation and Imputation - Generates sequential data using recurrent autoencoder architectures.

Learning kernels to maximize the power of MMD tests

Generative Adversarial Networks for High Energy Physics extended to a multi-layer calorimeter simulation

Code for the paper "Adversarially Regularized Autoencoders (ICML 2018)" by Zhao, Kim, Zhang, Rush and LeCun

Learning kernels to maximize the power of MMD tests

Generative Adversarial Networks for High Energy Physics extended to a multi-layer calorimeter simulation

Code for the paper "Adversarially Regularized Autoencoders (ICML 2018)" by Zhao, Kim, Zhang, Rush and LeCun