Overcoming Catastrophic Interference by Conceptors

Abstract

Catastrophic interference has been a major roadblock in the research of continual learning. Here we propose a variant of the back-propagation algorithm, "conceptor-aided back-prop" (CAB), in which gradients are shielded by conceptors against degradation of previously learned tasks. Conceptors have their origin in reservoir computing, where they have been previously shown to overcome catastrophic forgetting. CAB extends these results to deep feedforward networks. On the disjoint MNIST task CAB outperforms two other methods for coping with catastrophic interference that have recently been proposed in the deep learning field.

14 pages, 4 figures

References in corpus (2)

• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• Controlling Recurrent Neural Networks by Conceptors

Cited by in corpus (5)

• Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
• Overcoming catastrophic forgetting with hard attention to the task
• Linear Mode Connectivity in Multitask and Continual Learning
• Disturbance-immune Weight Sharing for Neural Architecture Search
• Controlling Recurrent Neural Networks by Diagonal Conceptors