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
  • [21] Character Recognition Using Teaching Learning Based Optimization
    Sahoo, Stuti
    Murty, S. Balarama
    Krishna, K. Murali
    [J]. PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON FRONTIERS OF INTELLIGENT COMPUTING: THEORY AND APPLICATIONS (FICTA) 2014, VOL 1, 2015, 327 : 737 - 744
  • [22] Fuzzy Hough transform and an MLP with fuzzy input output for character recognition
    Sural, S
    Das, PK
    [J]. FUZZY SETS AND SYSTEMS, 1999, 105 (03) : 489 - 497
  • [23] Optimal Parameters Of Bp Network For Character Recognition
    Yi, Hongjie
    Ji, Guangrong
    Zheng, Haiyong
    [J]. 2012 INTERNATIONAL CONFERENCE ON INDUSTRIAL CONTROL AND ELECTRONICS ENGINEERING (ICICEE), 2012, : 1757 - 1760
  • [24] Analysis of Multi-Layer Neural Network's Recognition Mechanism Using Alopex Algorithm
    Shintani, Hirohito
    Akutagawa, Masatake
    Nagashino, Hirofumi
    Pandya, Abhijit S.
    Kinouchi, Yohsuke
    [J]. WORLD CONGRESS ON MEDICAL PHYSICS AND BIOMEDICAL ENGINEERING 2006, VOL 14, PTS 1-6, 2007, 14 : 135 - +
  • [25] MLP neural network using constructive training algorithm: Application to face recognition and facial expression recognition
    [J]. Boughrara, Hayet (hayet.boughrara@laposte.net), 1600, Inderscience Enterprises Ltd., 29, route de Pre-Bois, Case Postale 856, CH-1215 Geneva 15, CH-1215, Switzerland (16):
  • [26] Handwritten character recognition system using modified Mahalanobis distance
    Kato, Nei
    Abe, Masato
    Nemoto, Yoshiaki
    [J]. Systems and Computers in Japan, 1997, 28 (01): : 46 - 55
  • [27] MINIMAL ALGORITHM FOR CHARACTER RECOGNITION
    WHITE, KL
    BATEMAN, BL
    [J]. TEXAS JOURNAL OF SCIENCE, 1972, 23 (04): : 561 - &
  • [28] Handwritten Numeral Recognition Using Modified BP ANN Structure
    Choudhary, Amit
    Rishi, Rahul
    Ahlawat, Savita
    [J]. ADVANCED COMPUTING, PT III, 2011, 133 : 56 - +
  • [29] Noisy digit recognition with MLP and HMMs using modified cost function in MCE training
    Salmela, P
    Lehtokangas, M
    Saarinen, J
    [J]. ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 1118 - 1121
  • [30] Extending MLP ANN hyper-parameters Optimization by using Genetic Algorithm
    Itano, Fernando
    de Abreu de Sousa, Miguel Angelo
    Del-Moral-Hernandez, Emilio
    [J]. 2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,