# Overcoming Catastrophic Interference by Conceptors

arXiv: https://arxiv.org/abs/1707.04853 · HTML: https://mlsanity.com/paper/1707.04853/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2017.

## Built on by (most cited first, 2 of 2)

- [Modality-Incremental Learning with Disjoint Relevance Mapping Networks for Image-based Semantic Segmentation](https://mlsanity.com/paper/2411.17610/) (2024)
- [Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned tasks](https://mlsanity.com/paper/2310.04741/) (2023)

## Abstract (arXiv)

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.