• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.842-846
• /
• 1993

Because of complexity, neural network is difficult to learn. So if internal representation[1] can be performed successfully, it is possible to use perceptron learning rule. As a result, learning is easier. Therefore the method of internal representations applied to the "XOR" problem, and the "spirals" problem. And then using the above results, the structure of neural network for computing is embodied.mputing is embodied.

• 한국광학회:학술대회논문집
• /
• 한국광학회 1991년도 제6회 파동 및 레이저 학술발표회 Prodeedings of 6th Conference on Waves and Lasers
• /
• pp.23-28
• /
• 1991

A single-layer neural network with 4$\times$4 input neurons and 4 output neurons is optically implemented. Holographic lenslet arrays are used for the e optical interconnection topology, a liquid crystal light valve(LCLV) is used for controlling optical interconection weights. Using a Perceptron learning rule, it classifics input patterns into 4 different categories. It is shown that the performance of the adaptive neural network depends on the learning rate, the correlation of input patterns, and the nonlinear characteristic properties of the liquid crystal light valve.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 SMICS 2004 International Symposium on Maritime and Communication Sciences
• /
• pp.1-5
• /
• 2004

In this paper, we propose a novel approach for evolving the architecture of a multi-layer neural network. Our method uses combined ART1 algorithm and Max-Min neural network to self-generate nodes in the hidden layer. We have applied the. proposed method to the problem of recognizing ID number in student identity cards. Experimental results with a real database show that the proposed method has better performance than a conventional neural network.

• 한국컴퓨터정보학회논문지
• /
• 제21권1호
• /
• pp.1-8
• /
• 2016

Convolutional neural network (CNN) consists of a few pairs of both convolution layer and subsampling layer. Thus it has more hidden layers than multi-layer perceptron. With the increased layers, the size of convolution mask ultimately determines the total number of weights in CNN because the mask is shared among input images. It also is an important learning factor which makes or breaks CNN's learning. Therefore, this paper proposes the best method to choose the convolution size and the number of layers for learning CNN successfully. Through our face recognition with vast learning examples, we found that the best size of convolution mask is 5 by 5 and 7 by 7, regardless of the number of layers. In addition, the CNN with two pairs of both convolution and subsampling layer is found to make the best performance as if the multi-layer perceptron having two hidden layers does.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.135-135
• /
• 2021

In water resources management, rainfall prediction with high accuracy is still one of controversial issues particularly in countries facing heavy rainfall during wet seasons in the monsoon climate. The aim of this study is to develop an artificial neural network (ANN) for predicting future six months of rainfall data (from April to September 2020) from daily meteorological data (from 1971 to 2019) such as rainfall, temperature, wind speed, and humidity at Seoul, Korea. After normalizing these data, they were trained by using a multilayer perceptron (MLP) as a class of the feedforward ANN with 15,000 neurons. The results show that the proposed method can analyze the relation between meteorological datasets properly and predict rainfall data for future six months in 2020, with an overall accuracy over almost 70% and a root mean square error of 0.0098. This study demonstrates the possibility and potential of MLP's applications to predict future daily rainfall patterns, essential for managing flood risks and protecting water resources.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.147-150
• /
• 1996

This paper describes controller design and implementation method for controlling the temperature distribution in a thermal stratified wind tunnel(TSWT) by using a neural network algorithm. It is impossible to derive a mathematical model of the relation between heat inputs and temperature outputs in the test section of the TSWT governed by a nonlinear turbulent flow. Thus inverse neural network models with a multi layer perceptron structure are used in a feedforward control loop and feedback control loop to generate an arbitrary temperature distribution in the test section of the TSWT.

• 한국항해항만학회지
• /
• 제32권8호
• /
• pp.589-596
• /
• 2008

선박의 접안운동을 자동화하기 위하여 인공신경망(Artificial Neural Network, 이하 ANN)에 의한 제어를 수행하였다. ANN은 시스템의 비선형성이 표현 가능하므로 접안운동과 같은 비선형성이 강한 조종운동에 적합하다. 입력층과 출력층 사이에 하나 이상의 중간층이 존재하는 다층 인식자(Multi-layer perceptron)를 사용하였고, 교사 데이터(Teaching data)와 역전파(Back-Propagation) 알고리즘을 사용하여 신경망의 출력값과 목표 출력값 사이의 오차가 최소가 되도록 신경망 학습을 수행하였다. 접안 시 저속조종 수학모델을 사용하여 접안 시뮬레이션을 수행하였으며, ANN의 입력층 성분(unit)이 8개인 구조와 6개인 구조의 접안 제어를 비교하였다. 시뮬레이션 결과, 두 ANN에 의하여 접안 경로 선택에 차이가 나타났으나 접안 조건은 모두 만족하였다.

• Nuclear Engineering and Technology
• /
• 제53권1호
• /
• pp.266-272
• /
• 2021

In the pulsed electron beam generators, such as plasma focus devices and linear induction accelerators whose electron pulse width is in the range of nanosecond and less, as well as in cases where there is no direct access to electron beam, like runaway electrons in Tokamaks, measurement of the electron energy spectrum is a technical challenge. In such cases, the indirect measurement of the electron spectrum by using the bremsstrahlung radiation spectrum associated with it, is an appropriate solution. The problem with this method is that the matrix equation between the two spectrums is an ill-conditioned equation, which results in errors of the measured X-ray spectrum to be propagated with a large coefficient in the estimated electron spectrum. In this study, a method based on the neural network and the MCNP code is presented and evaluated to recover the electron spectrum from the X-ray generated by collision of the electron beam with a target. Multilayer perceptron network showed good accuracy in electron spectrum recovery, so that for the X-ray spectrum with errors of 3% and 10%, the network estimated the electron spectrum with an average standard error of 8% and 11%, on all of the energy intervals.

• 융합신호처리학회논문지
• /
• 제2권2호
• /
• pp.111-118
• /
• 2001

본 연구에서는 패턴 인식용 다층 퍼셉트론 신경망을 순수 디지털 논리회로 모델로 구현할 수 있도록 새로운 논리뉴런의 구조, 디지털 정형 다층논리신경망 구조, 그리고 패턴인식의 응용을 위한 다단 다층논리 신경망 구조를 제안하고, 또한 제안된 구조는 매우 단순하면서도 효과적인 증가적인 가법적(Incremental Additive) 학습알고리즘이 존재함을 보였다.

• 전자공학회논문지B
• /
• 제31B권7호
• /
• pp.179-189
• /
• 1994

A two-phase neural network finds exact feasible solutions for a constrained optimization programming problem. The time-varying programming neural network is a modified steepest-gradient algorithm which solves time-varying optimization problems. In this paper, we propose a time-varying two-phase optimization neural network which incorporates the merits of the two-phase neural network and the time-varying neural network. The proposed algorithm is applied to system identification and function approximation using a multi-layer perceptron. Particularly training of a multi-layer perceptrion is regarded as a time-varying optimization problem. Our algorithm can also be applied to the case where the weights are constrained. Simulation results prove the proposed algorithm is efficient for solving various optimization problems.