서지주요정보
Optimal implementations of neural nets using a holographic interconnection method = 홀로그램 연결방법을 이용한 신경회로망의 광학적 구현
서명 / 저자 Optimal implementations of neural nets using a holographic interconnection method = 홀로그램 연결방법을 이용한 신경회로망의 광학적 구현 / Ju-Seog Jang.
저자명 Jang, Ju-Seog ; 장주석
발행사항 [대전 : 한국과학기술원, 1989].
Online Access 원문보기 원문인쇄

소장정보

등록번호

8000113

소장위치/청구기호

학술문화관(문화관) 보존서고

DEE 8937

휴대폰 전송

도서상태

이용가능

대출가능

반납예정일

초록정보

Highly interconnected simple analog processors that mimic biological neural networks are known to excel at certain collective computational tasks. In realization of such artificial neural networks, one main difficulty may be how to implement efficiently a large number of mutually weighted inter-connection between the simplified artificial neurons. In this thesis, optical implementations of neural network models using the holograms for three-dimensional interconnections in space have been studied. First, the Hopfield model for two-dimensional associative memory that requires parallel $N^4$ weighted interconnections is implemented with an N x N hologram array. Though the model has limited storage capacity, the implemented system is very simple. Second, quadratic associative memory model of neural networks that requires parallel $N^3$ weighted interconnections is implemented with an N x 1 hologram array and a Stanford matrixvector multiplier. The storage capacity per neuron of this scheme is increased by introducing a little more complexity. Third, to introduce the programmability, which is essential for adaptive networks, in these interconnection schemes, programmable higher-order interconnection method using holographic lenslet arrays and spatial light modulators are proposed. To demonstrate the feasibility of this interconnection scheme, a two-dimensionalquadratic associative memory that requires parallel $N^6$ weighted interconnections is implemented with two N x N holographic lenslet arrays and two spatial light modulators. Fourth, adaptive learning networks using our programmable interconnection scheme and a photorefractive crystal are proposed. Basic experiment for dynamic Hopfield-like networks is executed as an example of learning networks. Next, the concepts of neural net computations are applied to some engineering problems: matrix inversion and analog-to-digital conversion. It is shown that the neural net computations for these problems have potential advantage in speed due to their parallel information processing capabilities, as compared with the conventional methods. Simple experiments are also executed and their results are discussed in detail.

서지기타정보

서지기타정보
청구기호 {DEE 8937
형태사항 iii, 86 p. : 삽도 ; 26 cm
언어 영어
일반주기 Appendix : Stability criteria of the stored vectors in the neutal net models
저자명의 한글표기 : 장주석
지도교수의 영문표기 : Sang-Yung Shin
지도교수의 한글표기 : 신상영
학위논문 학위논문(박사) - 한국과학기술원 : 전기및전자공학과,
서지주기 Reference : p. 79-86
주제 Learning models (Stochastic processes)
Holographic interferometry.
Optical data processing.
Optical communications.
신경 회로망. --과학기술용어시소러스
홀로그램. --과학기술용어시소러스
광학 정보 처리. --과학기술용어시소러스
광 변조기. --과학기술용어시소러스
학습 모델. --과학기술용어시소러스
Neural networks (Computer science)
QR CODE qr code