Zauberzeug Learning Loop

Today, the number of applications and tasks that use AI is rapidly growing. It is used where the task is too difficult to solve for a human or requires a lot of manual work. While AI algorithms are black boxes most of the time, the success of an AI model highly correlates with the quality of the labeled data. 60% to 80% of the time spend training an AI model is data preparation. Of course, data preparation includes labeling. Moreover, a lot of data is needed to train and improve AI models. If time is crucial or the amount of data is limited, other solutions have to be used to create a satisfactory model. Often, an AI expert is needed to create such models. Therefore, we developed the Zauberzeug Learning Loop, a no-code web platform that uses Active Learning to reduce the amount of data needed. The system is currently tested in different projects and can be used in various fields of AI use cases like agriculture.