IEEE

Application of variational autoencoder network to real-time prediction of steel crown in the hot strip rolling mill process

Abstract: In the hot strip rolling mill (HSRM) process, accurate prediction and control of the strip crown are critical for quality assurance. In order to cope with this challenge, this study designed ...
GitHub

yanming-s/Denoising-VAE

This repository implements a Denoising Variational Autoencoder (DVAE) based on the U-Net architecture to remove various types of image noise. The model is trained on a subset of ImageNet data with ...

Novel AI platform accelerates discovery of chemical catalysts for industry

CatDRX is a generative AI framework developed at Institute of Science Tokyo, which enables the design of new chemical ...
IEEE

Spiking Generative Models Based on Variational Autoencoder and Adversarial Training

Deep neural networks (DNNs) have demonstrated exceptional performance across a variety of applications, yet they require substantial computing and power resources. In contrast, Spiking Neural Networks ...
GitHub

ti2ni1m/Image-Generation-with-Conditional-Variational-Autoencoder-C-VAE-and-Conditional-GAN-C-GAN-

In this project, I aim to create a set of images of Kuzushiji Japanese characters via the Kuzushiji-49 dataset using 2 graphical models which are Conditional-Variational Autoencoder(C-VAE), and ...
Visual Studio Magazine

Generating Synthetic Data Using a Variational Autoencoder with PyTorch

Generating synthetic data is useful when you have imbalanced training data for a particular class, for example, generating synthetic females in a dataset of employees that has many males but few ...