Overcoming Catastrophic Forgetting in Neural Networks

Editorial record

Plain-language summary

The method estimates how sensitive prior-task performance is to each weight using the Fisher information, then adds a quadratic penalty anchoring the important weights while leaving the rest free to adapt. A single network could learn a sequence of tasks and retain earlier ones where ordinary training would overwrite them. It turned catastrophic forgetting from a vague failure into a measurable, tractable problem and anchored the continual-learning literature.