Home Knowledge Base Continual Learning

Continual Learning is the family of training methodologies that enable a neural network to learn new tasks or absorb new data distributions sequentially without destroying the knowledge it acquired from earlier tasks — directly combating the fundamental failure mode known as catastrophic forgetting.

Why Catastrophic Forgetting Happens

Standard gradient descent treats parameter space as a blank slate. When a model trained on Task A is fine-tuned on Task B, the gradients for Task B freely overwrite the weights that encoded Task A. After just a few epochs, performance on Task A can drop to random chance even though the model excels on Task B.

Major Strategy Families

Engineering Tradeoffs

MethodForgetting RiskMemory CostCompute Overhead
EWCModerate (approximate protection)Low (Fisher diagonal only)Moderate (Fisher computation per task)
Replay BufferLow (direct rehearsal)Grows with tasksLow per step (small buffer samples)
Progressive NetsZero (frozen columns)High (parameters grow linearly)Forward pass cost grows per task

When Each Approach Fits

EWC and SI work well when the task sequence is short (5-10 tasks) and memory is constrained. Replay dominates when data storage is feasible and the number of tasks is large. Progressive networks suit hardware-constrained pipelines (such as robotics) where guaranteed zero-forgetting outweighs the parameter growth.

Continual Learning is the engineering bridge between static model training and real-world deployment — where data never stops arriving and retraining from scratch on every distribution shift is economically impossible.

continual learningcatastrophic forgettingelastic weight consolidationprogressive neural networklifelong learning

Explore 500+ Semiconductor & AI Topics

From EUV lithography to CUDA optimization — search the full knowledge base or chat with our AI assistant.