IEEE

Combining an Autoencoder and a Variational Autoencoder for Explaining the Machine Learning Model Predictions

Abstract: A method for explaining a deep learning model prediction is proposed. It uses a combination of the standard autoencoder and the variational autoencoder. The standard autoencoder is exploited ...
IEEE

Autoencoder for 4-Dimensional Fiber Orientation Distributions from Diffusion MRI

Abstract: Fiber orientation distributions (FODs) are widely used in connectome analysis based on diffusion MRI. Spherical har-monics (SPHARMs) are often used for the efficient repre-sentation of FODs; ...
GitHub

Evolutionary Adversarial Autoencoder for Unsupervised Anomaly Detection: Prototype Implementation.

The training objective combines multiple loss components: Total Loss = Reconstruction Loss + β×KL Loss + λ₁×Adversarial Loss(latent) + λ₂×Adversarial Loss(data) -ae_hidden_dim: Hidden layer size for ...
Scientific Research Publishing

Traffic Speed Prediction Based on Autoencoder and Deep Learning ()

Traffic prediction is the core of intelligent transportation system, and accurate traffic speed prediction is the key to optimize traffic management. Currently, the traffic speed prediction model ...
GitHub

MAFS: Masked Autoencoder for Infrared-Visible Image Fusion and Semantic Segmentation

Infrared-visible image fusion methods aim at generating fused images with good visual quality and also facilitate the performance of high-level tasks. Indeed, existing semantic-driven methods have ...