LEARNING BIAS IN NEURAL NETWORKS AND AN APPROACH TO CONTROLLING ITS EFFECTS IN MONOTONIC CLASSIFICATION

被引：8
|
作者：
ARCHER, NP [1 ]
WANG, SH [1 ]
机构：
[1] UNIV NEW BRUNSWICK,FAC BUSINESS,ST JOHN E2L 4L5,NB,CANADA
来源：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1993年 / 15卷 / 09期
关键词：
BACKPROPAGATION; LEARNING BIAS; MONOTONICALLY SEPARABLE; MONOTONIC BOUNDARY; MONOTONICITY; NEURAL NETWORK;
D O I：
10.1109/34.232084
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
As a learning machine, a neural network using the back-propagation training algorithm is subject to learning bias. This results in unpredictability of boundary generation behavior in pattern recognition applications, especially in the case of small training sample size. This research sugests that in a large class of pattern recognition problems, such as managerial and other problems possessing monotonicity properties, the effect of learning bias can be controlled by using multiarchitecture monotonic function neural networks.
引用
下载
收藏
页码：962 / 966
页数：5
相关论文
共 50 条
  • [31] Simplifying approach to node classification in Graph Neural Networks
    Maurya, Sunil Kumar
    Liu, Xin
    Murata, Tsuyoshi
    JOURNAL OF COMPUTATIONAL SCIENCE, 2022, 62
  • [32] Hybrid evolutionary approach for designing neural networks for classification
    Tan, ZH
    ELECTRONICS LETTERS, 2004, 40 (15) : 955 - 957
  • [33] Convolutional Neural Networks Approach for Music Genre Classification
    Cheng, Yu-Huei
    Chang, Pang-Ching
    Kuo, Che-Nan
    2020 INTERNATIONAL SYMPOSIUM ON COMPUTER, CONSUMER AND CONTROL (IS3C 2020), 2021, : 399 - 403
  • [34] An Approach for Thoracic Syndrome Classification with Convolutional Neural Networks
    Juneja, Sapna
    Juneja, Abhinav
    Dhiman, Gaurav
    Behl, Sanchit
    Kautish, Sandeep
    COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2021, 2021
  • [35] Wavelet neural networks with a hybrid learning approach
    Lin, Cheng-Jian
    JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 2006, 22 (06) : 1367 - 1387
  • [36] A new approach to the structural learning of neural networks
    Debnath, R
    Takahashi, H
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2004, E87A (06): : 1655 - 1658
  • [37] AutoDLCon: An Approach for Controlling the Automated Tuning for Deep Learning Networks
    Kotb, Hazem M.
    Elhelw, Mohamed
    Sakr, Sherif
    2020 IEEE SIXTH INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING SERVICE AND APPLICATIONS (BIGDATASERVICE 2020), 2020, : 158 - 165
  • [38] Transfer learning in hierarchical dialogue topic classification with neural networks
    Montenegro, Cesar
    Santana, Roberto
    Lozano, Jose A.
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [39] Learning algorithm for pattern classification using cellular neural networks
    Grassi, G
    Di Sciascio, E
    ELECTRONICS LETTERS, 2000, 36 (23) : 1941 - 1943
  • [40] Convolutional neural networks and extreme learning machines for malware classification
    Mugdha Jain
    William Andreopoulos
    Mark Stamp
    Journal of Computer Virology and Hacking Techniques, 2020, 16 : 229 - 244
12345