Name
Title | ||
|---|---|---|
Is deep learning better than kernel regression for functional connectivity prediction of fluid intelligence? |
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. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/PRNI.2018.8423958 | 2018 International Workshop on Pattern Recognition in Neuroimaging (PRNI) |
Keywords | Field | DocType |
Deep learning,fMRI,neuroimaging,Functional Connectivity,machine learning,kernel regression | Kernel (linear algebra),Human Connectome Project,Convolutional neural network,Computer science,Correlation,Artificial intelligence,Neuroimaging,Deep learning,Artificial neural network,Kernel regression | Conference |
ISBN | Citations | PageRank |
978-1-5386-6860-3 | 0 | 0.34 |
References | Authors | |
0 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tong He | 1 | 0 | 0.34 |
| Ru Kong | 2 | 25 | 1.87 |
| Avram J. Holmes | 3 | 49 | 3.52 |
| Sabuncu Mert R. | 4 | 1344 | 78.78 |
| Simon B. Eickhoff | 5 | 1297 | 79.68 |
| Danilo Bzdok | 6 | 185 | 9.75 |
| Jiashi Feng | 7 | 2165 | 140.81 |
| B. T. Thomas Yeo | 8 | 707 | 36.84 |