Abstract
In this paper, we introduce a data-dependent kernel called deep quasi-linear kernel, which can directly gain a profit from a pre-trained feedforward deep network. Firstly, a multi-layer gated bilinear classifier is formulated to mimic the functionality of a feed-forward neural network. The only difference between them is that the activation values of hidden units in the multi-layer gated bilinear classifier are dependent on a pre-trained neural network rather than a pre-defined activation function. Secondly, we demonstrate the equivalence between the multi-layer gated bilinear classifier and an SVM with a deep quasi-linear kernel. By deriving a kernel composition function, traditional optimization algorithms for a kernel SVM can be directly implemented to implicitly optimize the parameters of the multi-layer gated bilinear classifier. Experimental results on different data sets show that our proposed classifier obtains an ability to outperform both an SVM with a RBF kernel and the pre-trained feedforward deep network.
| Original language | English |
|---|---|
| Title of host publication | 2016 International Joint Conference on Neural Networks, IJCNN 2016 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1639-1645 |
| Number of pages | 7 |
| Volume | 2016-October |
| ISBN (Electronic) | 9781509006199 |
| DOIs | |
| Publication status | Published - 2016 Oct 31 |
| Event | 2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada Duration: 2016 Jul 24 → 2016 Jul 29 |
Other
| Other | 2016 International Joint Conference on Neural Networks, IJCNN 2016 |
|---|---|
| Country | Canada |
| City | Vancouver |
| Period | 16/7/24 → 16/7/29 |
Fingerprint
ASJC Scopus subject areas
- Software
- Artificial Intelligence
Cite this
A deep quasi-linear kernel composition method for support vector machines. / Li, Weite; Furuzuki, Takayuki; Chen, Benhui.
2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. p. 1639-1645 7727394.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A deep quasi-linear kernel composition method for support vector machines
AU - Li, Weite
AU - Furuzuki, Takayuki
AU - Chen, Benhui
PY - 2016/10/31
Y1 - 2016/10/31
N2 - In this paper, we introduce a data-dependent kernel called deep quasi-linear kernel, which can directly gain a profit from a pre-trained feedforward deep network. Firstly, a multi-layer gated bilinear classifier is formulated to mimic the functionality of a feed-forward neural network. The only difference between them is that the activation values of hidden units in the multi-layer gated bilinear classifier are dependent on a pre-trained neural network rather than a pre-defined activation function. Secondly, we demonstrate the equivalence between the multi-layer gated bilinear classifier and an SVM with a deep quasi-linear kernel. By deriving a kernel composition function, traditional optimization algorithms for a kernel SVM can be directly implemented to implicitly optimize the parameters of the multi-layer gated bilinear classifier. Experimental results on different data sets show that our proposed classifier obtains an ability to outperform both an SVM with a RBF kernel and the pre-trained feedforward deep network.
AB - In this paper, we introduce a data-dependent kernel called deep quasi-linear kernel, which can directly gain a profit from a pre-trained feedforward deep network. Firstly, a multi-layer gated bilinear classifier is formulated to mimic the functionality of a feed-forward neural network. The only difference between them is that the activation values of hidden units in the multi-layer gated bilinear classifier are dependent on a pre-trained neural network rather than a pre-defined activation function. Secondly, we demonstrate the equivalence between the multi-layer gated bilinear classifier and an SVM with a deep quasi-linear kernel. By deriving a kernel composition function, traditional optimization algorithms for a kernel SVM can be directly implemented to implicitly optimize the parameters of the multi-layer gated bilinear classifier. Experimental results on different data sets show that our proposed classifier obtains an ability to outperform both an SVM with a RBF kernel and the pre-trained feedforward deep network.
UR - http://www.scopus.com/inward/record.url?scp=85007275575&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85007275575&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2016.7727394
DO - 10.1109/IJCNN.2016.7727394
M3 - Conference contribution
AN - SCOPUS:85007275575
VL - 2016-October
SP - 1639
EP - 1645
BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016
PB - Institute of Electrical and Electronics Engineers Inc.
ER -