Self-organizing incremental neural networks for continual learning

Wiwatcharakoses, Chayut and Berrar, Daniel (2019). Self-organizing incremental neural networks for continual learning. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019), pp. 6476–6477.

DOI: https://doi.org/10.24963/ijcai.2019/927

Abstract

Continual learning systems can adapt to new tasks, changes in data distributions, and new information that becomes incrementally available over time. The key challenge for such systems is how to mitigate catastrophic forgetting, i.e., how to prevent the loss of previously learned knowledge when new tasks need to be solved. In our research, we investigate self-organizing incremental neural networks (SOINN) for continual learning from both stationary and non-stationary data. We have developed a new algorithm, SOINN+, that learns to forget irrelevant nodes and edges and is robust to noise.

Viewing alternatives

Metrics

Item Actions

Export

You can export this page using these formats Digital Object Identifier - DOI