Working Memory for Online Memory Binding Tasks: A Hybrid Model

TL;DR

This paper introduces a hybrid working memory model combining a feed-forward network with a random network, demonstrating effective online memory binding and a novel role for random networks in such tasks.

Contribution

The work presents the first use of random networks as flexible memory in online binding tasks, with learning confined to the feed-forward component.

Findings

The hybrid model performs well on various memory binding tasks.

Random networks can serve as effective temporary storage without learning.

The model simulates aspects of working memory with minimal training requirements.

Abstract

Working Memory is the brain module that holds and manipulates information online. In this work, we design a hybrid model in which a simple feed-forward network is coupled to a balanced random network via a read-write vector called the interface vector. Three cases and their results are discussed similar to the n-back task called, first-order memory binding task, generalized first-order memory task, and second-order memory binding task. The important result is that our dual-component model of working memory shows good performance with learning restricted to the feed-forward component only. Here we take advantage of the random network property without learning. Finally, a more complex memory binding task called, a cue-based memory binding task, is introduced in which a cue is given as input representing a binding relation that prompts the network to choose the useful chunk of memory. To our knowledge, this is the first time that random networks as a flexible memory is shown to play an important role in online binding tasks. We may interpret our results as a candidate model of working memory in which the feed-forward network learns to interact with the temporary storage random network as an attentional-controlling executive system.