21 citations · 38 across the 2 of their papers we have counts for
3 papers
stat.ML2021★ 21 cited
Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA
Hermanni Hälvä, Sylvain Le Corff, Luc Lehéricy +4
We introduce a new general identifiable framework for principled disentanglement referred to as Structured Nonlinear Independent Component Analysis (SNICA). Our contribution is to…
stat.ML2020★ 17 cited
Hidden Markov Nonlinear ICA: Unsupervised Learning from Nonstationary Time Series
Hermanni Hälvä, Aapo Hyvärinen
Recent advances in nonlinear Independent Component Analysis (ICA) provide a principled framework for unsupervised feature learning and disentanglement. The central idea in such wor…
cs.NE2018
Computational Graph Approach for Detection of Composite Human Activities
Niko Reunanen, Ville Könönen, Hermanni Hälvä +3
Existing work in human activity detection classifies physical activities using a single fixed-length subset of a sensor signal. However, temporally consecutive subsets of a sensor…