On retrieval of lost functions for feedforward neural networks using re-learning

被引：0

作者：

Kamiura, N

Isokawa, T

Yamato, K

Matsui, N

机构：

[1] Univ Hyogo, Himeji Inst Technol, Grad Sch Engn, Himeji, Hyogo 6712201, Japan

[2] Hyogo Med Univ, Dept Econ & Informat Sci, Kakogawa 6750101, Japan

来源：

KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 3, PROCEEDINGS | 2004年 / 3215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：

This paper proposes the re-learning for feedforward neural networks where weight faults would occur. The sequences of target outputs are encoded by means of single-parity-check codes so that a single-bit error caused by the faults can be on-line detected at the output layer. The re-learning is made every time a network produces the error, and its lost function is retrieved. The proposed scheme can easily achieve high MTTF (Mean Time To Failure).

引用

页码：491 / 497

页数：7

共 50 条

[1] Reduction of Difference among Trained Neural Networks by Re-Learning
Liu, Yong
[J]. 2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 1880 - 1884
[2] A fast learning algorithm of feedforward neural networks by using novel error functions
Jiang, MH
Deng, BX
Gielen, G
Tang, XF
Ruan, QQ
Yuan, BZ
[J]. 2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 1171 - 1174
[3] Interpolation functions of feedforward neural networks
Li, HX
Lee, ES
[J]. COMPUTERS & MATHEMATICS WITH APPLICATIONS, 2003, 46 (12) : 1861 - 1874
[4] Inverse mapping of continuous functions using feedforward neural networks
Deif, HM
Zurada, JM
[J]. 1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, 1997, : 744 - 748
[5] Topology of Learning in Feedforward Neural Networks
Gabella, Maxime
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (08) : 3588 - 3592
[6] Automatic scaling using gamma learning for feedforward neural networks
Engelbrecht, AP
Cloete, I
Geldenhuys, J
Zurada, JM
[J]. FROM NATURAL TO ARTIFICIAL NEURAL COMPUTATION, 1995, 930 : 374 - 381
[7] Learning Properties of Feedforward Neural Networks Using Dual Numbers
Okawa, Yuto
Nitta, Tohru
[J]. 2021 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2021, : 187 - 192
[8] Weighted Learning for Feedforward Neural Networks
Rong-Fang Xu
Thao-Tsen Chen
Shie-Jue Lee
[J]. JournalofElectronicScienceandTechnology, 2014, 12 (03) : 299 - 304
[9] Weighted Learning for Feedforward Neural Networks
Rong-Fang Xu
Thao-Tsen Chen
Shie-Jue Lee
[J]. Journal of Electronic Science and Technology, 2014, (03) : 299 - 304
[10] Data-Driven Learning of Feedforward Neural Networks with Different Activation Functions
Dudek, Grzegorz
[J]. ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING (ICAISC 2021), PT I, 2021, 12854 : 66 - 77

← 1 2 3 4 5 →