Optimization of MLP/BP for character recognition using a modified alopex algorithm

被引:0
|
作者
Shintani, Hirohito [1 ]
Akutagawa, Masatake [1 ]
Nagashino, Hirofumi [2 ]
Pandya, Abhijit [3 ]
Kinouchi, Yohsuke [1 ]
机构
[1] Univ Tokushima, Fac Engn, 2-1mNubanu Hisabhuna, Tokushima 7708506, Japan
[2] Univ Tokushima, Sch Hlth Sci, 3-18-15,Kuramoto, Tokushima 7708509, Japan
[3] Florida Atlant Univ, Dept Comp Sci & Engn, Boca Raton, FL 33431 USA
关键词
Neural network; Alopex algorithm; character recognition; intelligent systems;
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
It is difficult to determine the recognition mechanism in the neurons of a neural network trained for pattern recognition due to the non-linear nature of neural networks. This paper describes a recognition mechanism of a four-layer back propagation neural network using Alopex algorithm. We have developed a small-scale, four-layered neural network model for simple character recognition, which can recognize the patterns transformed by affined conversion. Alopex algorithm is an iterative and stochastic processing method, which was proposed for optimization of a given cost function. In this case the receptive fields of the neurons in the output layers are obtained using the Alopex algorithm.
引用
收藏
页码:371 / 379
页数:9
相关论文
共 50 条
  • [1] Optical Character Recognition System Using BP Algorithm
    Park, Sang Sung
    Jung, Won Gyo
    Shin, Young Geun
    Jang, Dong-Sik
    [J]. INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2008, 8 (12): : 118 - 124
  • [2] Mongolian character recognition using multilayer perceptron (MLP)
    Batsaikhan, O
    Singh, YP
    [J]. ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 621 - 625
  • [3] MLP Neural Network Using Modified Constructive Training Algorithm: Application to Face Recognition
    Boughrara, Hayet
    Chtourou, Mohamed
    Ben Amar, Chokri
    Chen, Liming
    [J]. 2014 FIRST INTERNATIONAL IMAGE PROCESSING, APPLICATIONS AND SYSTEMS CONFERENCE (IPAS), 2014,
  • [4] Research of Digital Character Recognition Technology Based on BP Algorithm
    Wei, Xianmin
    [J]. ADVANCES IN COMPUTER SCIENCE, ENVIRONMENT, ECOINFORMATICS, AND EDUCATION, PT I, 2011, 214 : 551 - 555
  • [5] Iranian License Plate Character Recognition Using Mixture of MLP Experts
    Nejati, Mansour
    Pourghassem, Hossein
    Majidi, Ali
    [J]. 2013 INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS AND NETWORK TECHNOLOGIES (CSNT 2013), 2013, : 219 - 223
  • [6] An alopex based evolutionary optimization algorithm
    Institute of Automation, East China University of Science and Technology, Shanghai 200237, China
    [J]. Moshi Shibie yu Rengong Zhineng, 2009, 3 (452-456):
  • [7] Character recognition using parallel BP neural network
    Yang, Feng
    Yang, Fan
    [J]. 2008 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING, VOLS 1 AND 2, PROCEEDINGS, 2008, : 1595 - 1599
  • [8] A modified Adaboost algorithm for Chinese handwritten character recognition
    Fu, Qiang
    Ding, Xiaoqing
    Liu, Changsong
    [J]. Gaojishu Tongxin/Chinese High Technology Letters, 2009, 19 (04): : 331 - 336
  • [9] Circle BP Algorithm for MLP Neural Network
    CHEN Jianyong
    [J]. Semiconductor Photonics and Technology, 1998, (03) : 46 - 49+59
  • [10] Engineering Character Recognition Algorithm and Application Based on BP Neural Network
    Rong, Chen
    Yu Luqian
    [J]. ADVANCES IN SWARM INTELLIGENCE, ICSI 2018, PT II, 2018, 10942 : 380 - 388