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

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[1,2], 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.

References

1. Liu, T., Floros, D., Pitsianis, N. & Sun, X. Digraph Clustering by the BlueRed Method. in 2021 IEEE High Performance Extreme Computing Conference (HPEC) 1–7 (2021). doi:10.1109/HPEC49654.2021.9622834.
2. Pitsianis, N., Floros, D., Liu, T. & Sun, X. Parallel Clustering with Resolution Variation. in 2023 IEEE High Performance Extreme Computing Conference (HPEC) 1–8 (IEEE, Boston, MA, USA, 2023). doi:10.1109/HPEC58863.2023.10363552.

Recommended citation: Juntang Wang†, Yihan Wang†, Hao Wu, Dongmian Zou, Shixin Xu (2025). "Brain-Inspired Perspective on Configurations: Unsupervised Similarity and Early Cognition." 15th International Conference on Brain Inspired Cognitive Systems (BICS 2025).
Download Paper