A Brain-inspired Computational Model for Human-like Concept Learning

TL;DR

This paper introduces a brain-inspired computational model for human-like concept learning that integrates multisensory and text-based representations through a semantic control system, achieving human-like cognition in neural networks.

Contribution

The study presents a novel spiking neural network model that mimics human concept learning by combining multisensory and text-derived representations inspired by neuroscience and psychology.

Findings

Model closely aligns with human concept representations

Effective handling of diverse and imbalanced data sources

Achieves human-like concept learning performance

Abstract

Concept learning is a fundamental aspect of human cognition and plays a critical role in mental processes such as categorization, reasoning, memory, and decision-making. Researchers across various disciplines have shown consistent interest in the process of concept acquisition in individuals. To elucidate the mechanisms involved in human concept learning, this study examines the findings from computational neuroscience and cognitive psychology. These findings indicate that the brain's representation of concepts relies on two essential components: multisensory representation and text-derived representation. These two types of representations are coordinated by a semantic control system, ultimately leading to the acquisition of concepts. Drawing inspiration from this mechanism, the study develops a human-like computational model for concept learning based on spiking neural networks. By effectively addressing the challenges posed by diverse sources and imbalanced dimensionality of the two forms of concept representations, the study successfully attains human-like concept representations. Tests involving similar concepts demonstrate that our model, which mimics the way humans learn concepts, yields representations that closely align with human cognition.