지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2009.8
- 수록면
- 5,008 - 5,013 (6page)
이용수
초록· 키워드
오류제보하기
In order to provide a guideline about the number of hidden neurons N<SUP>(h)</SUP>and learning rate for large-scale neural networks from the viewpoint of stable learning, the authors try to formulate the boundary of stable learning roughly, and to adjust it to the actual learning results of random number mapping problems. It is confirmed in the simulation that the hidden-output connection weights become small as the number of hidden neurons becomes large, and also that the trade-off in the learning stability between input-hidden and hidden-output connections exists. Finally, two equations N<SUP>(h)</SUP>=N<SUP>(i)</SUP>N<SUP></SUP> and n=32/N<SUP>(i)</SUP>N<SUP>(o)</SUP> are roughly introduced where N<SUP>(i)</SUP> and N<SUP>(o)</SUP> are the number of input and output neurons respectively even though further adjustment is necessary for other problems or conditions. Keywords: large-scale layered neural network, error back propagation, supervised learning, learning stability
목차
Abstract
1. Introduction
2. Formulation
3. Simulation
4. Tuning of Formulation
5. Conclusion
Reference
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Supervised Competitive Learning Neural Network with Flexible Output Layer
한국지능시스템학회 논문지
2001 .12
-
신경회로망과 실험계획법을 이용한 타이어의 장력 추정
Journal of the Korean Society for Precision Engineering
2011 .07
-
신경회로망을 이용한 직류전동기의 센서리스 속도제어
Journal of Advanced Marine Engineering and Technology (JAMET)
2004 .01
-
Exploring Knowledge Distribution in Neural Network Parameter
대한전자공학회 학술대회
2019 .06
-
LEARNING OF A MULTI-VALUED NEURAL NETWORK AND ITS APPLICATION
JTC-CSCC : Joint Technical Conference on Circuits Systems, Computers and Communications
1992 .01
-
T-S 퍼지 신경망 시스템에 대한 H∞ 안정화 학습 법칙
제어로봇시스템학회 국내학술대회 논문집
2016 .03
-
Neural Network Training Using a GMDH Type Algorithm
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2005 .03
-
심층 신경망 압축을 위한 중복뉴런 제거 기법
대한전자공학회 학술대회
2017 .11
-
Learning Performance of Multilayer Neural Network with Threshold Neurons
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
1997 .01
-
A Study on New Control Mechanisms of Memory
대한전자공학회 학술대회
1992 .10
-
Design of a Neural Chip for Classifying Iris Flowers based on CMOS Analog Neurons
센서학회지
2019 .01
-
딥러닝의 모형과 응용사례
지능정보연구
2016 .06
-
New criteria to fix number of hidden neurons in multilayer perceptron networks for wind speed prediction
Wind & structures
2014 .01
-
Propagation Method of Pulses in a 2-Dimensional Neural Network Using Pulse-Type Hardware Neuron Models
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2005 .07
-
Implementation of Self-adaptive System using the Algorithm of Neural Network Learning Gain
International Journal of Control Automation and Systems
2008 .06
-
The Construction of a Layered Neural Network with an Optimum Number of Hidden Units
ICONIP : International Conference On Neural Information Processing
1994 .01
-
역전파 알고리즘을 이용한 경계결정의 구성에 관한 연구
정보학연구
2005 .01
-
0.35 ㎛ CMOS 공정을 이용한 Integrate and Fire Neuron model 구현
대한전자공학회 학술대회
2007 .07
-
0.35㎛ CMOS 공정을 이용한 Integrate and Fire Neuron model 구현
대한전자공학회 학술대회
2007 .07
-
Implementation of Self-adaptive System using the Algorithm of Neural Network Learning Gain
International Journal of Control, Automation, and Systems
2008 .06
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2014-569-000761663