Catastrophic forgetting is a term from artificial intelligence and also affects areas such as automation and Industry 4.0. It describes a problem that occurs when an artificial intelligence (AI), while learning new tasks, suddenly loses or „forgets“ what it has previously learned.
Imagine a robot is first learning how to tighten screws. Later, you teach it to hammer in nails. If the robot completely forgets how to screw things in while learning the new skill, this is called catastrophic forgetting. This makes AI less useful, as it cannot retain the knowledge it previously had.
This problem is particularly critical when AI systems are intended to flexibly perform many different tasks – for example, in a smart factory where machines are constantly used for various jobs.
Catastrophic forgetting is therefore a central theme in the development of modern AI solutions. Innovative methods are being developed so that AI systems not only learn new things but also retain their old knowledge – similar to how humans do not forget everything prior when learning new skills.















