Researchers Use SHAP to Link Disentangled Autoencoder Latent Space to Real Flow Fields

A new XAI study applies SHAP attribution to the latent space of disentangled autoencoders, identifying the flow features each latent variable encodes and connecting causal analysis in latent space to real fluid flow structures.

2026-11-04 ~ 2026-11-04 · 2 related posts

• New XAI study links latent-space causality to real flow structures via SHAP — ricardovinuesa · 2026-11-04

1 near-duplicate retellings: ricardovinuesa