Skip to content
GCC AI Research

Unscented Autoencoder

arXiv · · Notable

Research NLP LLM CV Arabic AI

Summary

The paper introduces the Unscented Autoencoder (UAE), a novel deep generative model based on the Variational Autoencoder (VAE) framework. The UAE uses the Unscented Transform (UT) for a more informative posterior representation compared to the reparameterization trick in VAEs. It replaces Kullback-Leibler (KL) divergence with the Wasserstein distribution metric and demonstrates competitive performance in Fréchet Inception Distance (FID) scores.

Keywords

Autoencoder · VAE · Unscented Transform · Generative Models · Wasserstein metric

Read original article →

Get the weekly digest

Top AI stories from the GCC region, every week.