Aapo Hyvärinen



ArXiv: Variational Autoencoders and Nonlinear ICA: A Unifying Framework

UAI2019: Causal Discovery with General Non-Linear Relationships Using Non-Linear ICA

AISTATS2019: Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning

AISTATS2019: Estimation of Non-Normalized Mixture Models and Clustering Using Deep Representation

Arxiv: Neural Empirical Bayes

NeuroImage: Decoding attentional states for neurofeedback: Mindfulness vs. wandering thoughts

Github: Code for Time-Contrastive Learning

Neuroinformatics Group at University of Helsinki

Neuroinformatics is widely defined as the cross-fertilization of information-processing and mathematical sciences on the one hand, and neural and cognitive sciences on the other.

Our group works on different aspects of neuroinformatics related to machine learning:

  • We apply machine learning models on neuroimaging data, in particular MEG.
  • We model the visual system in the brain by analyzing the statistical structure of the natural input images.
  • We develop the relevant theory of statistical machine learning, typically unsupervised.

The group is located at U Helsinki and at the Gatsby Unit, UCL

Former members and long-term visitors

Alexander Zhigalov, Jukka-Pekka Kauppi, Jouni Puuronen, Hande Celikkanat, Hiroshi Morioka, Michael Gutmann, Kun Zhang, Pavan Ramkumar, Hiroaki Sasaki, Jun-ichiro Hirayama, Urs Köster, Shohei Shimizu, Antti Hyttinen, Miika Pihlaja, Patrik Hoyer, Cristina Campi, Doris Entner, Hugo Eyherabide, Jarmo Hurri, Mika Inki, Ilmari Kurki, Jussi Lindgren, Yao Lu, Jukka Perkiö, Asun Vicente.