Specifically, we propose a Local Residual Quantized Variational AutoEncoder (Local RQ-VAE) to learn prototype vectors that represent the local details of high-quality images. Then we propose a ...

This project implements a system for detecting anomalies in time series data collected from Prometheus. It uses an LSTM (Long Short-Term Memory) autoencoder model built with TensorFlow/Keras to learn ...

The model was trained using a combination of reconstruction loss, Kullback–Leibler (KL) divergence, and classification loss, optimized for balanced performance. For peptide generation, latent vectors ...

Specifically, a variational autoencoder firstly trains a generative distribution and extracts reconstruction based features. Then we adopt a deep brief network to estimate the component mixture ...