Is deep learning better than kernel regression for functional connectivity prediction of fluid intelligence?
Lists
Only you see this
Abstract
In recent years, deep learning has transformed the field of machine learning. In the field of neuroimaging, there are increasing interests in adopting deep learning techniques. However, deep neural networks (DNNs) usually need large quantity of data to perform well, which is often lacking in neuroimaging. In this work, we evaluated three different DNNs (fully-connected neural network, BrainNetCNN [1], and graph convolutional neural network [2]) for functional connectivity (FC)-based prediction of fluid intelligence using the Human Connectome Project. These DNNs were compared with kernel regression, a classical machine learning algorithm. Our results suggested that the DNNs did not outperform kernel regression. However, we do not preclude the possibility that with more participants or different FC features, DNNs might eventually outperform their classical counterpart.
BibTeX
@inproceedings{he2018is,
author = {Tong He and Ru Kong and Avram J. Holmes and Mert R. Sabuncu and Simon B. Eickhoff and Danilo Bzdok and Jiashi Feng and B. T. Thomas Yeo},
title = {{Is deep learning better than kernel regression for functional connectivity prediction of fluid intelligence?}},
booktitle = {PRNI},
year = {2018},
doi = {10.1109/prni.2018.8423958},
}Loading related content...