A model for structured information representation in neural networks

TL;DR

This paper presents a neural network model that uses Hebbian plasticity to assign words to semantic roles, enabling structured reasoning and information manipulation in a biologically plausible way.

Contribution

It demonstrates how semantic role binding emerges in spiking neural networks through Hebbian learning, aligning with experimental data and enabling complex cognitive functions.

Findings

Semantic role binding emerges via Hebbian plasticity in spiking neural networks.

The model supports structured information retrieval, copying, and comparison.

Results align with experimental evidence on neural organization of abstract reasoning.

Abstract

Humans possess the capability to reason at an abstract level and to structure information into abstract categories, but the underlying neural processes have remained unknown. Experimental evidence has recently emerged for the organization of an important aspect of abstract reasoning: for assigning words to semantic roles in a sentence, such as agent (or subject) and patient (or object). Using minimal assumptions, we show how such a binding of words to semantic roles emerges in a generic spiking neural network through Hebbian plasticity. The resulting model is consistent with the experimental data and enables new computational functionalities such as structured information retrieval, copying data, and comparisons. It thus provides a basis for the implementation of more demanding cognitive computations by networks of spiking neurons.