Zero-shot learning is a term from artificial intelligence that plays a particularly important role in automation and big and smart data. It describes the ability of AI systems to solve tasks or recognise objects without having seen examples beforehand.
Normally, AI models need to be trained on a lot of data to distinguish, for example, cats from dogs. With zero-shot learning, on the other hand, the system can draw on its existing knowledge to tackle new, unknown tasks. This saves time and resources because training data doesn't need to be collected for every new situation.
A vivid example: A language assistant already understands many requests in German and English. Now it is asked a question in Spanish, without having specific training data for it. Thanks to zero-shot learning, the assistant still manages to answer the Spanish question reasonably correctly or grasp its meaning by using its existing knowledge of languages and contexts.
Zero-shot learning makes artificial intelligence more versatile and efficient, especially in areas where new situations need to be recognised and handled flexibly and quickly.
Deutsch 
English (UK)