Study presents new method for explainable AI

Artificial intelligence is already in widespread use, yet it is still difficult to understand how an AI system reaches its decisions. Scientists at the Fraunhofer Heinrich-Hertz-Institut (HHI) and the Berlin Institute for the Foundations of Learning and Data (BIFOLD) at TU Berlin have collaborated for many years to make AI explainable. Now the scientists led by Prof. Thomas Wiegand (Fraunhofer HHI, BIFOLD), Prof. Wojciech Samek (Fraunhofer HHI, BIFOLD) and Dr. Sebastian Lapuschkin (Fraunhofer HHI) have achieved another milestone.