Cargando…
Multi-Timescale Memory Dynamics Extend Task Repertoire in a Reinforcement Learning Network With Attention-Gated Memory
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, w...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6055065/ https://www.ncbi.nlm.nih.gov/pubmed/30061819 http://dx.doi.org/10.3389/fncom.2018.00050 |
Sumario: | 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. |
---|