A neural network for modeling human concept formation, understanding and communication

TL;DR

This paper introduces the CATS Net, a dual-module neural network that models human-like concept formation, understanding, and communication, aligning with neurocognitive data and enabling transfer of knowledge through conceptual representations.

Contribution

The work presents a novel dual-module neural network framework that captures human concept abstraction, transfer, and communication, bridging computational modeling with neurocognitive findings.

Findings

Concept spaces align with human semantic models and brain responses.

Gating mechanisms in the model mirror semantic control in the brain.

The framework provides insights into human conceptual cognition and artificial intelligence.

Abstract

A remarkable capability of the human brain is to form more abstract conceptual representations from sensorimotor experiences and flexibly apply them independent of direct sensory inputs. However, the computational mechanism underlying this ability remains poorly understood. Here, we present a dual-module neural network framework, the CATS Net, to bridge this gap. Our model consists of a concept-abstraction module that extracts low-dimensional conceptual representations, and a task-solving module that performs visual judgement tasks under the hierarchical gating control of the formed concepts. The system develops transferable semantic structure based on concept representations that enable cross-network knowledge transfer through conceptual communication. Model-brain fitting analyses reveal that these emergent concept spaces align with both neurocognitive semantic model and brain response structures in the human ventral occipitotemporal cortex, while the gating mechanisms mirror that in the semantic control brain network. This work establishes a unified computational framework that can offer mechanistic insights for understanding human conceptual cognition and engineering artificial systems with human-like conceptual intelligence.