Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Juntang, Wang, Yihan, Wu, Hao, Zou, Dongmian, Xu, Shixin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.19229
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915754572513280
author Wang, Juntang
Wang, Yihan
Wu, Hao
Zou, Dongmian
Xu, Shixin
author_facet Wang, Juntang
Wang, Yihan
Wu, Hao
Zou, Dongmian
Xu, Shixin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19229
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Brain-Inspired Perspective on Configurations: Unsupervised Similarity and Early Cognition
Wang, Juntang
Wang, Yihan
Wu, Hao
Zou, Dongmian
Xu, Shixin
Machine Learning
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.
title Brain-Inspired Perspective on Configurations: Unsupervised Similarity and Early Cognition
topic Machine Learning
url https://arxiv.org/abs/2510.19229