Submodular neural network is better than modular neural network and support vector machines for personal verification

被引：0
|
作者：
Nagano, T [1 ]
Hirahara, M [1 ]
Eguchi, H [1 ]
机构：
[1] Hosei Univ, Fac Engn, Tokyo 1848584, Japan
来源：
PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4 | 2003年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A sub-modular neural network (SMNN) proposed a few years ago is compared with the usual modular neural network (MNN) and support vector machines (SVM) in terms of pattern recognition performance. Some computer simulation results showed that SMNN was much superior to MNN and SVM as for rejection rates of patterns in unlearned classes under the condition that they gave almost the same recognition rates for patterns in learned classes. These results strongly suggest that SMNN is more suitable for personal verification systems than the other two as such systems require high rejection rate for patterns in unlearned classes.
引用
收藏
页码：2152 / 2156
页数：5
相关论文
共 50 条
  • [1] Support Vector Machines with Neural Network
    Yanagimoto, Hidekazu
    NEW TRENDS IN INTELLIGENT SOFTWARE METHODOLOGIES, TOOLS AND TECHNIQUES, 2017, 297 : 124 - 138
  • [2] A Projection Neural Network for Training Support Vector Machines
    Liu, Fengqiu
    Zhang, Hongxu
    Qin, Sitian
    2016 31ST YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC), 2016, : 298 - 302
  • [3] A compact neural network for training support vector machines
    Yang, Yun
    He, Qiaochu
    Hu, Xiaolin
    NEUROCOMPUTING, 2012, 86 : 193 - 198
  • [4] FPGA implementation of dynamic neural network for support vector machines
    Liu, Han
    Yin, Song
    Liu, Ding
    Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University, 2010, 44 (07): : 962 - 967
  • [5] Dynamic neural network based training for support vector machines
    Hou, ZG
    Gupta, MM
    NAFIPS 2004: ANNUAL MEETING OF THE NORTH AMERICAN FUZZY INFORMATION PROCESSING SOCIETY, VOLS 1AND 2: FUZZY SETS IN THE HEART OF THE CANADIAN ROCKIES, 2004, : 259 - 264
  • [6] Biologically relevant neural network architectures for support vector machines
    Jandel, Magnus
    NEURAL NETWORKS, 2014, 49 : 39 - 50
  • [7] A Neural Network Approach for Least Squares Support Vector Machines Learning
    Liu, Han
    Liu, Ding
    PROCEEDINGS OF THE 48TH IEEE CONFERENCE ON DECISION AND CONTROL, 2009 HELD JOINTLY WITH THE 2009 28TH CHINESE CONTROL CONFERENCE (CDC/CCC 2009), 2009, : 7297 - 7302
  • [8] SAR ATR by a Combination of Convolutional Neural Network and Support Vector Machines
    Wagner, Simon A.
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2016, 52 (06) : 2861 - 2872
  • [9] Use of support vector machines and neural network in diagnosis of neuromuscular disorders
    Güler N.F.
    Koçer S.
    Journal of Medical Systems, 2005, 29 (3) : 271 - 284
  • [10] Fast modular network implementation for support vector machines
    Huang, GB
    Mao, KZ
    Siew, CK
    Huang, DS
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (06): : 1651 - 1663
12345