Transfer between long-term and short-term memory using Conceptors
Neural and Evolutionary Computing
2020-03-27 v1 Machine Learning
Adaptation and Self-Organizing Systems
Neurons and Cognition
Machine Learning
Abstract
We introduce a recurrent neural network model of working memory combining short-term and long-term components. e short-term component is modelled using a gated reservoir model that is trained to hold a value from an input stream when a gate signal is on. e long-term component is modelled using conceptors in order to store inner temporal patterns (that corresponds to values). We combine these two components to obtain a model where information can go from long-term memory to short-term memory and vice-versa and we show how standard operations on conceptors allow to combine long-term memories and describe their effect on short-term memory.
Keywords
Cite
@article{arxiv.2003.11640,
title = {Transfer between long-term and short-term memory using Conceptors},
author = {Anthony Strock and Nicolas Rougier and Xavier Hinaut},
journal= {arXiv preprint arXiv:2003.11640},
year = {2020}
}