Interpreting rate-distortion of variational autoencoder and using model uncertainty for anomaly detection

DOI10.1007/s10472-021-09728-4OpenAlexW3127222865MaRDI QIDQ2163846

Panos M. Pardalos, Seonho Park, George Adosoglou

Publication date: 11 August 2022

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2005.01889

zbMATH Keywords

information theorymodel uncertaintyanomaly detectionrate-distortion theoryvariational autoencoderMC dropout

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Uses Software

• MNIST
• CIFAR
• AdaGrad
• Adam
• Fashion-MNIST

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Support vector data description
• Combining stochastic adaptive cubic regularization with negative curvature for nonconvex optimization
• Estimating the Support of a High-Dimensional Distribution
• Deep-Cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes
• Optimization Methods for Large-Scale Machine Learning
• Sharpening Jensen's Inequality

This page was built for publication: Interpreting rate-distortion of variational autoencoder and using model uncertainty for anomaly detection