FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation. (arXiv:2206.00050v3 [cs.LG] UPDATED)

The ability to estimate epistemic uncertainty is often crucial when deploying
machine learning in the real world, but modern methods often produce
overconfident, uncalibrated uncertainty predictions. A common approach to
quantify epistemic uncertainty, usable across a wide class of prediction
models, is to train a model ensemble. In a naive implementation, the ensemble
approach has high computational cost and high memory demand. This challenges in
particular modern deep learning, where even a single deep network is already
demanding in terms …

arxiv deep learning ensemble feature film linear probabilistic deep learning