The term neural-symbolic integration originates from the fields of artificial intelligence, digital transformation, big data and smart data. It describes the approach of combining the advantages of two different types of artificial intelligence: machine learning (neural networks) and symbolic AI (rules and logic).
Neural networks are particularly good at recognising patterns in large amounts of data, for example when recognising images. Symbolic AI, on the other hand, works with clear rules and is therefore better at modelling logical thinking, for example when a decision needs to be derived from "if-then" rules.
Neural-symbolic integration combines these two methods: A system can both learn from data and explain its knowledge and make it comprehensible. This is particularly important in areas such as medicine or finance, where decisions need to be justified.
One example: an intelligent assistance system in a hospital can analyse X-ray images using neural networks, but can also explain the findings in a comprehensible way using medical rules. Both doctors and patients benefit from transparent, high-performance technology.
Deutsch 
English (UK)