서지주요정보
Fokker-planck equation을 이용한 신경망 훈련과정인 back-propagation 방법의 분석 = Analysis of back-pro-pagation method in neural network training process using fokker-planck equation
서명 / 저자 Fokker-planck equation을 이용한 신경망 훈련과정인 back-propagation 방법의 분석 = Analysis of back-pro-pagation method in neural network training process using fokker-planck equation / 도종관.
저자명 도종관 ; Do, Jong-Gwan
발행사항 [대전 : 한국과학기술원, 1998].
Online Access 원문보기 원문인쇄

소장정보

등록번호

8008443

소장위치/청구기호

학술문화관(문화관) 보존서고

MPH 98001

SMS전송

도서상태

이용가능

대출가능

반납예정일

초록정보

To understand the statistical behavior of the neural network training process, I adopt back-propagation as a basic method of the neural network training process, and analyze the evolution of the probability density in a Fokker-Planck equation. And I choose a simple feed-forward neural network which consists of two input neurons, one output neuron, and two weights. The evolution of the probability density in a Fokker-Planck equation can be understood as a distribution, which represents the various paths that weights change per one sample data in a back-propagation method. The Probability density spreads out to the direction of error minimum weight point in the beginning. After some numerical iterations the peak located at error minimum point increases while the other peaks decrease very rapidly. Finally only one sharp peak located at error minimum point remains. And at that point, all jump moments in a Fokker-Planck equation have zero value.

서지기타정보

서지기타정보
청구기호 {MPH 98001
형태사항 ii, 56 p. : 삽도 ; 26 cm
언어 한국어
일반주기 저자명의 영문표기 : Jong-Gwan Do
지도교수의 한글표기 : 고인규
지도교수의 영문표기 : In-Gyu Koh
학위논문 학위논문(석사) - 한국과학기술원 : 물리학과,
서지주기 참고문헌 : p. 55-56
QR CODE qr code