Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness

no code implementations • 31 Oct 2018 • Raphael Suter, Đorđe Miladinović, Bernhard Schölkopf, Stefan Bauer

The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks.

Disentanglement