"Artificial neural networks can suffer from catastrophic forgetting, in which learning a new task causes the network to forget how to perform previous tasks. While previous studies have proposed various methods that can alleviate forgetting over small numbers (<10) of tasks, it is uncertain whether they can prevent forgetting across larger numbers of tasks. In this study, we propose a neuroscience-inspired scheme, called “context-dependent gating,” in which mostly nonoverlapping sets of units are active for any one task. Importantly, context-dependent gating has a straightforward implementation, requires little extra computational overhead, and when combined with previous methods to stabilize connection weights, can allow networks to maintain high performance across large numbers of sequentially presented tasks."
Model Type: Connectionist Network
Model Concept(s): Learning; Reinforcement Learning
Simulation Environment: Python (web link to model)
Implementer(s): Masse, Nicolas Y [masse at uchicago.edu]; Grant, Gregory D [dfreedman at uchicago.edu]
References:
Masse NY, Grant GD, Freedman DJ. (2018). Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization. Proceedings of the National Academy of Sciences of the United States of America. 115 [PubMed]