Brain-Inspired Perspective on Configurations: Unsupervised Similarity and Early Cognition

TL;DR

This paper introduces a brain-inspired clustering framework called configurations that models early cognitive processes like categorization and novelty detection, demonstrating competitive performance and stability in dynamic scenarios.

Contribution

It presents a novel finite-resolution clustering method with attraction-repulsion dynamics, evaluated by a new metric, mheatmap, to assess hierarchical and dynamic properties.

Findings

Achieves 87% AUC in novelty detection

Shows 35% improved stability during dynamic category changes

Performs competitively on standard clustering metrics

Abstract

Infants discover categories, detect novelty, and adapt to new contexts without supervision-a challenge for current machine learning. We present a brain-inspired perspective on configurations, a finite-resolution clustering framework that uses a single resolution parameter and attraction-repulsion dynamics to yield hierarchical organization, novelty sensitivity, and flexible adaptation. To evaluate these properties, we introduce mheatmap, which provides proportional heatmaps and reassignment algorithm to fairly assess multi-resolution and dynamic behavior. Across datasets, configurations are competitive on standard clustering metrics, achieve 87% AUC in novelty detection, and show 35% better stability during dynamic category evolution. These results position configurations as a principled computational model of early cognitive categorization and a step toward brain-inspired AI.