Rate-Coding Bundle Memory: A Unified Model of Memory and Control for Symbolic Computation in the Brain
Artificial IntelligenceComputation and LanguageSymbolic Computation
Summary
The authors propose a model called Rate-Coding Bundle Memory (RCBM) to explain how our brain thinks. Their model mixes two ideas: connectionist networks (like brain-like neural connections) and symbolic systems (like using symbols and rules). RCBM uses a way of representing information called rate coding within a memory system that can quickly store and recall symbols. This helps explain mental abilities like learning from one experience, telling similar things apart, and combining information. The authors suggest their model could help us better understand thinking and build improved cognitive models.
Authors
Teun van Gils, Rowan P. Sommers, Markus Ostarek, Peter Hagoort
Abstract
We propose a neurobiologically plausible model of cognition that combines the advantages of connectionist and symbolic systems, and that can explain a wide range of cognitive phenomena. This model, called Rate-Coding Bundle Memory (RCBM), is based on the Symbolic Subsystem Hypothesis, which posits that the brain implements a symbolic subsystem within its fundamentally connectionist nature. RCBM is a hybrid model that uses rate coding to represent symbols in a continuous space, and it uses a bundle memory system to store and retrieve these symbols. The model is capable of solving a wide range of cognitive phenomena, including one-shot learning, pattern separation, and the binding problem. We argue that RCBM provides a promising framework for understanding the nature of cognition, and that it can be used to develop more sophisticated models of cognition in the future.