Towards neural networks that provably know when they don't know

Understand

It has recently been shown that ReLU networks produce arbitrarily over-confident predictions far away from the training data.

• Thus, ReLU networks do not know when they don't know.
• However, this is a highly important property in safety critical applications.
• In the context of out-of-distribution detection (OOD) there have been a number of proposals to mitigate this problem but none of them are able to make any mathematical guarantees.