Improving the efficiency of counting defects by learning RBF nets with MAD loss

被引：0
|
作者：
Rafajlowicz, Ewaryst [1 ]
机构：
[1] Wroclaw Univ Technol, Inst Comp Engn Control & Robot, PL-50370 Wroclaw, Poland
来源：
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING - ICAISC 2008, PROCEEDINGS | 2008年 / 5097卷
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：
The method of using a lateral histogram for evaluating the number of holes (e.g., defects) from images is known to be fast but rather inaccurate. Our aim is to propose a method of improving its performance by learning, but keeping the speed of the original method. This task is accomplished by considering a multiclass pattern recognition problem with linearly ordered labels and a loss function, which measures absolute deviations of decisions from true classes.
引用
收藏
页码：146 / 153
页数：8
相关论文
共 50 条
  • [1] MAD loss in pattern recognition and RBF learning
    Rafajlowicz, Ewaryst
    Skubalska-Rafajlowicz, Ewa
    [J]. ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING - ICAISC 2008, PROCEEDINGS, 2008, 5097 : 671 - 680
  • [2] Deterministic annealing learning of the radial basis function nets for improving the regression ability of RBF network
    Zheng, NN
    Zhang, ZH
    Zheng, HB
    Gang, S
    [J]. IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL III, 2000, : 601 - 607
  • [3] RBF nets, mixture experts, and Bayesian Ying-Yang learning
    Xu, L
    [J]. NEUROCOMPUTING, 1998, 19 (1-3) : 223 - 257
  • [4] Method for Improving Gradient Boosting Learning Efficiency Based on Modified Loss Functions
    Korolev, N. S.
    Senko, O. V.
    [J]. AUTOMATION AND REMOTE CONTROL, 2022, 83 (12) : 1935 - 1943
  • [5] Method for Improving Gradient Boosting Learning Efficiency Based on Modified Loss Functions
    N. S. Korolev
    O. V. Senko
    [J]. Automation and Remote Control, 2022, 83 : 1935 - 1943
  • [6] OPTICAL METHOD FOR IMPROVING THE COUNTING EFFICIENCY OF SCINTILLATION COUNTERS
    DAVIS, RH
    GRAVES, JD
    [J]. PHYSICAL REVIEW, 1949, 75 (09): : 1461 - 1461
  • [7] A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
    Do, Thanh-Toan
    Tran, Toan
    Reid, Ian
    Kumar, Vijay
    Hoang, Tuan
    Carneiro, Gustavo
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 10396 - 10405
  • [8] IMPROVING LEARNING EFFICIENCY BY THE LECTURE METHOD
    SHUPE, DS
    [J]. ENGINEERING EDUCATION, 1979, 69 (05): : 406 - 408
  • [9] An adaptive learning algorithm aimed at improving RBF network generalization ability
    Sun, J
    Shen, RM
    Yang, F
    [J]. AL 2002: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2002, 2557 : 363 - 373
  • [10] NEW METHOD TO REDUCE COSMIC BACKGROUND WITHOUT LOSS OF COUNTING EFFICIENCY
    IMPERIALE, C
    [J]. JOURNAL OF NUCLEAR MEDICINE AND ALLIED SCIENCES, 1978, 22 (03): : 125 - 131
12345