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

页码：962 / 966

页数：5

共 50 条

[1] Partially Monotonic Learning for Neural Networks
Trindade, Joana
Vinagre, Joao
Fernandes, Kelwin
Paiva, Nuno
Jorge, Alipio
ADVANCES IN INTELLIGENT DATA ANALYSIS XIX, IDA 2021, 2021, 12695 : 12 - 23
[2] Distributional reinforcement learning with unconstrained monotonic neural networks
Theate, Thibaut
Wehenkel, Antoine
Bolland, Adrien
Louppe, Gilles
Ernst, Damien
NEUROCOMPUTING, 2023, 534 : 199 - 219
[3] A Preliminary Approach for using Metric Learning in Monotonic Classification
Luis Suarez, Juan
Gonzalez-Almagro, German
Garcia, Salvador
Herrera, Francisco
ADVANCES AND TRENDS IN ARTIFICIAL INTELLIGENCE: THEORY AND PRACTICES IN ARTIFICIAL INTELLIGENCE, 2022, 13343 : 773 - 784
[4] Active Learning Approach for EEG Classification using Neural Networks: A review
Sebek, Jakub
Schaabova, Hana
Krajca, Vladimir
2019 E-HEALTH AND BIOENGINEERING CONFERENCE (EHB), 2019,
[5] Cancers classification based on deep neural networks and emotional learning approach
Jafarpisheh, Noushin
Teshnehlab, Mohammad
IET SYSTEMS BIOLOGY, 2018, 12 (06) : 258 - 263
[6] A Learning Framework for Controlling Spiking Neural Networks
Narayanan, Vignesh
Ritt, Jason T.
Li, Jr-Shin
Ching, ShiNung
2019 AMERICAN CONTROL CONFERENCE (ACC), 2019, : 211 - 216
[7] Avoiding Unintended Bias in Toxicity Classification with Neural Networks
Morzhov, Sergey
PROCEEDINGS OF THE 26TH CONFERENCE OF OPEN INNOVATIONS ASSOCIATION FRUCT, 2020, : 314 - 320
[8] A novel classification approach based on Extreme Learning Machine and Wavelet Neural Networks
Yahia, Siwar
Said, Salwa
Zaied, Mourad
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (19-20) : 13869 - 13890
[9] A Supervised Learning approach on Rice Variety Classification using Convolutional Neural Networks
Castillo, Louie John L.
Galindo, Juvy Amor M.
Rosal, Jamie Eduardo C.
PROCEEDINGS OF 2019 6TH INTERNATIONAL CONFERENCE BIOINFORMATICS RESEARCH AND APPLICATIONS (ICBRA 2019), 2019, : 18 - 23
[10] A novel classification approach based on Extreme Learning Machine and Wavelet Neural Networks
Siwar Yahia
Salwa Said
Mourad Zaied
Multimedia Tools and Applications, 2020, 79 : 13869 - 13890

← 1 2 3 4 5 →