The term progressive neural networks originates from the fields of artificial intelligence, automation, big data and smart data. Progressive neural networks are a special type of artificial neural network that are designed to improve over time. They can transfer knowledge that they have learnt in one task to new tasks and thus continue to develop.
Think of progressive neural networks as an employee who uses the experience they have already gained for each new task to work faster and more efficiently. For example, such a network can initially learn to recognise cats in pictures. Later, it can use this knowledge to recognise other animals in pictures without having to start from scratch.
The special thing about progressive neural networks is that, unlike traditional models, they "learn" without losing the old knowledge. This saves development costs and makes applications in areas such as automation or smart data analysis particularly effective. As a result, progressive neural networks specifically support companies in solving complex tasks more flexibly and driving innovation faster.
Deutsch 
English (UK)