Title | ||
---|---|---|
Multi-timescale memory dynamics in a reinforcement learning network with attention-gated memory. |
Abstract | ||
---|---|---|
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. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Neurons and Cognition | Synaptic tagging,Computer science,Repertoire,Artificial intelligence,Synaptic plasticity,Stimulus (physiology),Cognition,Augment,Artificial neural network,Machine learning,Reinforcement learning |
DocType | Volume | Citations |
Journal | abs/1712.10062 | 0 |
PageRank | References | Authors |
0.34 | 15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marco Martinolli | 1 | 0 | 0.34 |
Wulfram Gerstner | 2 | 2437 | 410.08 |
Aditya Gilra | 3 | 0 | 1.35 |