Fig.1

Concept

Catastrophic forgetting

Catastrophic forgetting is the tendency of a neural network to lose previously learned capabilities when you train it on a new task. The weights that encoded the old skill get overwritten by gradient updates optimizing the new objective, because standard training has no term…

The rest of “Catastrophic forgetting” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library

Catastrophic forgetting, explained · Fig. 1