Titlul prezentarii: Proximity Curves for Potential-Based Clustering
Data si ora: miercuri 23.06.2021, 10:00-10:45
Prezentare online: https://meet.google.com/src-fgqr-max
Rezumat: The talk introduces the concept of proximity curve and a new clustering algorithm for a finite set of data points. Each point is endowed with a potential constructed by means of a multi-dimensional Cauchy density, contributing to an overall anisotropic potential function. Guided by the steepest descent algorithm, the data points are successively visited and removed one by one, and, at each stage, the overall potential is updated and the magnitude of its local gradient is calculated. The result is a finite sequence of tuples, the proximity curve, whose pattern is analysed to give rise to a deterministic clustering. The results are consistent with the proposed theoretical framework and data properties, and open new approaches and applications to consider data processing from different perspectives and interpret data attributes’ contribution to patterns.The talk is based on the paper:
Csenki, A., Neagu, D., Torgunov, D., Micic, N., (2020) Proximity Curves for Potential-Based Clustering. J Classif 37, 671–695 (2020). Available online at: https://doi.org/10.1007/s00357-019-09348-y
Scurt bio: Daniel Neagu is Professor of Computing with the University of Bradford from 2011 and the AI Research Group leader. His research focuses on machine learning techniques applied in (automotive) engineering, product safety, toxicology, healthcare, data quality, and big data.