Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yuwei Wang, Yi Zeng

TL;DR

The paper introduces a brain-inspired computational framework for human-like concept learning that fuses multisensory (grounded) and text-derived (linguistic) representations via a spiking neural network architecture coordinated by a semantic control mechanism. It demonstrates that coordinated integration outperforms single-modality and naive concatenation baselines across multiple human-judgment benchmarks, addressing dimensional imbalances with a spatial-temporal cooperation scheme. The approach leverages Poisson spike coding, a multisensory processing module, a text-derived module, and spatial/temporal coordination to generate human-like concept representations, with case studies illustrating closer alignment to human cognition. These results advance cognitive modeling and have implications for brain-inspired AI agents capable of more human-like concept understanding and reasoning.

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.

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

TL;DR

The paper introduces a brain-inspired computational framework for human-like concept learning that fuses multisensory (grounded) and text-derived (linguistic) representations via a spiking neural network architecture coordinated by a semantic control mechanism. It demonstrates that coordinated integration outperforms single-modality and naive concatenation baselines across multiple human-judgment benchmarks, addressing dimensional imbalances with a spatial-temporal cooperation scheme. The approach leverages Poisson spike coding, a multisensory processing module, a text-derived module, and spatial/temporal coordination to generate human-like concept representations, with case studies illustrating closer alignment to human cognition. These results advance cognitive modeling and have implications for brain-inspired AI agents capable of more human-like concept understanding and reasoning.

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.
Paper Structure (16 sections, 9 equations, 3 figures, 6 tables)

This paper contains 16 sections, 9 equations, 3 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Results
  3. Two Types of Concept Representation Datasets
  4. Similar Concepts Test
  5. Performance Metric
  6. Results and Analysis
  7. Case Study
  8. Parameters Analysis
  9. Discussion
  10. Methods
  11. Poisson Coding
  12. Multisensory Information Processing Module
  13. Text-derived Information Processing Module
  14. Semantic Cooperate Module
  15. Spatial Cooperate
  16. ...and 1 more sections

Figures (3)

  • Figure 1: The Framework of the Brain-inspired Computational Model on Human-like Concept Learning
  • Figure 2: The Relation Between Representation Diversity and Spatial Stride, Temporal Stride
  • Figure 3: The Computational Model on Human-like Concept Learning