標題: Image Classification Based on the Boost Convolutional Neural Network
作者: Lee, Shin-Jye
Chen, Tonglin
Yu, Lun
Lai, Chin-Hui
科技管理研究所
Institute of Management of Technology
關鍵字: Convolutional neural network;ensemble learning;deep learning;boosting
公開日期: 1-Jan-2018
摘要: Convolutional neural networks (CNNs), which are composed of multiple processing layers to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent years. However, these models can have millions of parameters and many layers, which are difficult to train, and sometimes several days or weeks are required to tune the parameters. Within this paper, we present the usage of a trained deep convolutional neural network model to extract the features of the images, and then, used the AdaBoost algorithm to assemble the Softmax classifiers into recognizable images. This method resulted in a 3% increase of accuracy of the trained CNN models, and dramatically reduced the retraining time cost, and thus, it has good application prospects.
URI: http://dx.doi.org/10.1109/ACCESS.2018.2796722
http://hdl.handle.net/11536/144746
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2018.2796722
期刊: IEEE ACCESS
Volume: 6
起始頁: 12755
結束頁: 12768
Appears in Collections:Articles