A long way towards reliable and robust machine learning
* Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay
There has been substantial progress in the area of robust and reliable machine learning but there is still a long way to go. This talk will provide an overview of work in the area of out-of-distribution detection and adversarial robustness. It will discuss potential ways forward also with regard to regulatory processes for safety-critical applications.