Orientation and scale based weights initialization scheme for deep convolution neural networks. Asia-Pacific Journal of Information Technology and Multimedia, 9 (2). pp. 103-112. ISSN 2289-2192 (2020)
Abstract
Image classification is generally about the understanding of information in the images concerned. The more the system able to understand the image contains, the more effective it will be in classifying desired images. Recent work has shown that the convolutional neural network (CNN) paradigm is useful for obtaining more accurate image classification results. A crucial component in the CNN is the convolution filters which consist of a series of predefined filter weight initialization values. However, most initialization schemes used in the deep convolutional neural networks are mainly to deal with vanishing gradient problems. Thus, selecting optimal weights are crucial to improve convergence and minimize the complexity which can enhance the generalization performance. One possible solution is to replace the standard weights with parameterized filters that proven to be efficient in extracting useful features such as Gabor filter bank.
| Item Type: | Article |
|---|---|
| Keywords: | Convolutional neural network, Gabor filter, Machine learning, Weight Initializer |
| Taxonomy: | By Subject > Computer & Mathematical Sciences > Statistics |
| Local Content Hub: | Subjects > Computer and Mathematical Sciences |
| Depositing User: | Muslim Ismail @ Ahmad |
| Date Deposited: | 20 Feb 2021 00:06 |
| Last Modified: | 20 Feb 2021 00:06 |
| Related URLs: |
Actions (login required)
 |
View Item |