AI Forest is an indoor woodland that hides a lot of mushrooms.
With an app based on an Artificial Intelligence (AI) system, visitors are supposed to fill their digital basket. The aim is to prepare a delicious mushroom goulash with as many different mushrooms as possible, but none that are inedible. The AI helps with the decision: To pick it up or leave it behind? How well does the app explain why it classifies a certain mushroom as edible or poisonous?
A key challenge of Artificial Intelligence is that the acceptance of Machine Learning (ML) algorithms is limited by their inability to “explain” their decisions in a way that is understandable for humans.
Researchers and policy makers are therefore calling for algorithmic accountability through Explainable AI (XAI). However, how to achieve the goal of Explainable AI in different usage contexts and in view of different target groups, especially non-experts, remains poorly understood.