Abstract
The paper presented a systematic evaluation of the weight sparsity regularization schemes for the deep neural networks applied to the whole brain resting-state functional magnetic resonance imaging data. The weight sparsity regularization was deployed between the visible and hidden layers of the Gaussian-Bernoulli restricted Boltzmann machine (GB-RBM), in which the L0-norm based non-zero value ratio and L1-/L2-norm based Hoyer's sparseness were used to define the weight sparsity. Also, the weight sparsity regularization schemes between the two consecutive layers (i.e. layer-wise) and between the layer and the node in the subsequent layer (i.e. node-wise) were compared in terms of the convergence property. Finally, the reproducibility of 10 sets of weight features extracted from the GB-RBMs trained using 10 sets of random initial weights was evaluated.
Original language | English |
---|---|
Title of host publication | 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 6150-6154 |
Number of pages | 5 |
ISBN (Electronic) | 9781509041176 |
DOIs | |
Publication status | Published - 2017 Jun 16 |
Event | 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States Duration: 2017 Mar 5 → 2017 Mar 9 |
Other
Other | 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 |
---|---|
Country/Territory | United States |
City | New Orleans |
Period | 17/3/5 → 17/3/9 |
Keywords
- Deep neural network
- Gaussian-Bernoulli restricted Boltzmann machine
- Hoyer's sparseness
- Human Connectome Project
- weight sparsity
ASJC Scopus subject areas
- Software
- Signal Processing
- Electrical and Electronic Engineering