activity
20232026
most citedPFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse

6 citations · 7 across the 5 of their papers we have counts for

collaborators
Showing 2025Show all

2 papers · 1 filter

cs.LG2025★ 1 cited

Feature Space Topology Control via Hopkins Loss

Einari Vaaras, Manu Airaksinen

Feature space topology refers to the organization of samples within the feature space. Modifying this topology can be beneficial in machine learning applications, including dimensi…

cs.CL2025

Investigating Affect Mining Techniques for Annotation Sample Selection in the Creation of Finnish Affective Speech Corpus

Kalle Lahtinen, Einari Vaaras, Liisa Mustanoja +1

Study of affect in speech requires suitable data, as emotional expression and perception vary across languages. Until now, no corpus has existed for natural expression of affect in…