On the role of neurogenesis in overcoming catastrophic forgetting

Autor:	Parisi, German I., Ji, Xu, Wermter, Stefan
Rok vydání:	2018
Předmět:	Computer Science - Neural and Evolutionary Computing Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Lifelong learning capabilities are crucial for artificial autonomous agents operating on real-world data, which is typically non-stationary and temporally correlated. In this work, we demonstrate that dynamically grown networks outperform static networks in incremental learning scenarios, even when bounded by the same amount of memory in both cases. Learning is unsupervised in our models, a condition that additionally makes training more challenging whilst increasing the realism of the study, since humans are able to learn without dense manual annotation. Our results on artificial neural networks reinforce that structural plasticity constitutes effective prevention against catastrophic forgetting in non-stationary environments, as well as empirically supporting the importance of neurogenesis in the mammalian brain. Comment: Accepted to NIPS'18 Workshop on Continual Learning
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1811.02113 Zobrazit plný text záznamu View this record from Arxiv