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

[21] All-Transfer Learning for Deep Neural Networks and Its Application to Sepsis Classification
Sawada, Yoshihide
Sato, Yoshikuni
Nakada, Toru
Ujimoto, Kei
Hayashi, Nobuhiro
ECAI 2016: 22ND EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, 285 : 1586 - 1587
[22] Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
Meirom, Eli A.
Maron, Haggai
Mannor, Shie
Chechik, Gal
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
[23] Subspace learning and hopfield neural networks in biomedical classification
Lin, Feng
BASIC & CLINICAL PHARMACOLOGY & TOXICOLOGY, 2019, 125 : 144 - 145
[24] Transfer Learning for Leaf Classification with Convolutional Neural Networks
Esmaeili, Hassan
Phoka, Thanathorn
2018 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER SCIENCE AND SOFTWARE ENGINEERING (JCSSE), 2018, : 191 - 196
[25] Classification with Stochastic Learning Methods and Convolutional Neural Networks
Astudillo N.M.
Bolman R.
Sirakov N.M.
SN Computer Science, 2020, 1 (3)
[26] Feedforward kernel neural networks, generalized least learning machine, and its deep learning with application to image classification
Wang, Shitong
Jiang, Yizhang
Chung, Fu-Lai
Qian, Pengjiang
APPLIED SOFT COMPUTING, 2015, 37 : 125 - 141
[27] A combined approach of convolutional neural networks and machine learning for visual fault classification in photovoltaic modules
Venkatesh, Sridharan Naveen
Sugumaran, Vaithiyanathan
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART O-JOURNAL OF RISK AND RELIABILITY, 2022, 236 (01) : 148 - 159
[28] Federated Learning with Deep Neural Networks: A Privacy-Preserving Approach to Enhanced ECG Classification
Weimann K.
Conrad T.O.F.
IEEE Journal of Biomedical and Health Informatics, 2024, 28 (11) : 1 - 9
[29] Active Learning With Convolutional Neural Networks for Hyperspectral Image Classification Using a New Bayesian Approach
Mario Haut, Juan
Paoletti, Mercedes E.
Plaza, Javier
Li, Jun
Plaza, Antonio
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2018, 56 (11): : 6440 - 6461
[30] A new site classification approach based on neural networks
Yaghmaei-Sabegh, Saman
Tsang, Hing-Ho
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING, 2011, 31 (07) : 974 - 981

← 1 2 3 4 5 →