Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics

Tong He (1) , Ru Kong (1) , Avram J Holmes (2) , Minh Quang Nguyen (1) , Mert Sabuncu (3) , Simon B. Eickhoff (4) , Danilo Bzdok (5, 6, 7) , Jiashi Feng (1) , B T Thomas Yeo (1)

1 NUS - National University of Singapore
2 Massachusetts General Hospital [Boston]
3 CSAIL - Computer Science and Artificial Intelligence Laboratory [Cambridge]
4 FZJ - Forschungszentrum Jülich GmbH | Centre de recherche de Jülich | Jülich Research Centre
5 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data
6 NEUROSPIN - Service NEUROSPIN
7 Department of Psychiatry, Psychotherapy and Psychosomatics [Aachen]

Domaines: Intelligence artificielle [cs.AI]

Tong He, Ru Kong, Avram J Holmes, Minh Quang Nguyen, Mert Sabuncu, et al.. Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics. NeuroImage, 2019, pp.116276. ⟨10.1016/j.neuroimage.2019.116276⟩. ⟨hal-02314718⟩