期刊
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
卷 12, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fncom.2018.00050
关键词
reinforcement learning; memory; attention; synaptic plasticity; eligibility trace; synaptic tagging
资金
- European Research Council (Multirules) [268689]
- Swiss National Science Foundation (Sinergia) [CRSII2_147636]
- European Commission Horizon 2020 Framework Program (H2020) (Human Brain Project) [720270]
- Swiss National Science Foundation (SNF) [CRSII2_147636] Funding Source: Swiss National Science Foundation (SNF)
The interplay of reinforcement learning and memory is at the core of several recent neural network models, such as the Attention-Gated MEmory Tagging (AuGMEnT) model. While successful at various animal learning tasks, we find that the AuGMEnT network is unable to cope with some hierarchical tasks, where higher-level stimuli have to be maintained over a long time, while lower-level stimuli need to be remembered and forgotten over a shorter timescale. To overcome this limitation, we introduce a hybrid AuGMEnT, with leaky (or short-timescale) and non-leaky (or long-timescale) memory units, that allows the exchange of low-level information while maintaining high-level one. We test the performance of the hybrid AuGMEnT network on two cognitive reference tasks, sequence prediction and 12AX.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据