English

Multi-timescale memory dynamics in a reinforcement learning network with attention-gated memory

Neurons and Cognition 2019-02-19 v1 Machine Learning Neural and Evolutionary Computing Machine Learning

Abstract

Learning and memory are intertwined in our brain and their relationship is at the core of several recent neural network models. In particular, the Attention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning network with an emphasis on biological plausibility of memory dynamics and learning. We find that the AuGMEnT network does not solve 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 hybrid AuGMEnT, with leaky or short-timescale and non-leaky or long-timescale units in memory, that allow to exchange lower-level information while maintaining higher-level one, thus solving both hierarchical and distractor tasks.

Keywords

Cite

@article{arxiv.1712.10062,
  title  = {Multi-timescale memory dynamics in a reinforcement learning network with attention-gated memory},
  author = {Marco Martinolli and Wulfram Gerstner and Aditya Gilra},
  journal= {arXiv preprint arXiv:1712.10062},
  year   = {2019}
}
R2 v1 2026-06-22T23:31:45.564Z