What's wrong with classes? The theory of Knowledge

Alessandro Chiancone (1, 2, 3)

1 TU Graz - Graz University of Technology [Graz]
2 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
3 GIPSA-SAIGA - GIPSA - Signal et Automatique pour la surveillance, le diagnostic et la biomécanique

This paper wants to investigate the deepest meaning of the word class that is often used in machine learning and classification as a well-defined concept. This adventure will lead the reader to the fundamentals of Mathematics like set theory from Zermelo-Fraenkel. This will be our start, like is all Mathematics, to understand how well defined is the class concept. A broader theory will be outlined with the courageous attempt to give an homogenous framework to deal with machine learning problems.

Mots clés: Machine learning; Theory of Knowledge; Image processing

Domaines: Statistiques [math.ST]; Analyse numérique [math.NA]

Alessandro Chiancone. What's wrong with classes? The theory of Knowledge. [Research Report] GIPSA-lab. 2015. ⟨hal-01113112v2⟩