Self-Supervised Variational Auto-Encoders

Density estimation, compression, and data generation are crucial tasks in artificial intelligence. Variational Auto-Encoders (VAEs) constitute a single framework to achieve these goals. Here, we present a novel class of generative models, called <i>self-supervised Variational Auto-Encoder</...

Full description

Bibliographic Details
Main Authors: Ioannis Gatopoulos, Jakub M. Tomczak
Format: Article
Language:English
Published: MDPI AG 2021-06-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/23/6/747