• 전자공학회논문지B
• /
• 제33B권10호
• /
• pp.90-97
• /
• 1996

This paper presents an efficient parallel implementation and its performance evaluations of a SOFM neural netowrk on the multicomputer. We investigate the parallel performance as the size of a neural network N, the number of the patterns L, and the number of the processors p increase. We propose an analytica performance evaluation model for eac of the parallel implementations and verified the validity of the model through experiments. Analytical result show that the number of processors for a maximum speedup of the network decomposition nd the training-set decomposition increases in proportion to .root.N and .root.L, respectively. The performances of the both decompositions depend on the number of training patterns L and the size of the neural network N and, if L.geq.0.423N, the performance of trhe training-set decomposition is proved to be better than that of the network decomposition.

• 제어로봇시스템학회논문지
• /
• 제8권4호
• /
• pp.338-344
• /
• 2002

In this paper, neural network force tracking control is proposed. The conventional impedance function is reformulated to have direct farce tracking capability. Neural network is used to compensate for all the uncertainties such as unknown robot dynamics, unknown environment stiffness, and unknown environment position. On line training signal of farce error for neural network is formulated. A large x-y table is built as a test-bed and neural network loaming algorithm is implemented on a DSP board mounted in a PC. Experimental studies of farce tracking on unknown environment for x-y table robot are presented to confirm the performance of the proposed technique.

• 산업공학
• /
• 제10권3호
• /
• pp.145-153
• /
• 1997

This paper deals with constructing a scheduling system for a mold manufacturing factory. The scheduling system is composed of 4 submodules such as pre-processor, neural network training, neural networks and simulation. Pre-processor analyzes the condition of workshop and generates input data to neural networks. Network training module is performed by using the condition of workshop, performance measures, and dispatching rules. Neural networks module presents the most optimized dispatching rule, based on previous training data according to the current condition of workshop. Simulation module predicts the earliest completion date of a mold by forward scheduling with the presented dispatching rules, and suggests a possible issue date of a material by backward tracking. The system developed shows a great potential when applied in real mold factory for automotive parts.

• 융합신호처리학회논문지
• /
• 제24권2호
• /
• pp.90-96
• /
• 2023

합성곱 신경망을 비롯하여 딥러닝 신경망의 학습에서 많은 양의 훈련데이터의 확보는 과적합 현상을 피하고 우수한 성능을 가지기 위해서 매우 중요하다. 하지만, 딥러닝 신경망에서의 레이블화된 훈련데이터의 확보는 실제로는 매우 제한적이다. 이를 극복하기 위해, 이미 획득한 훈련데이터를 변형, 조작 등으로 추가로 훈련데이터를 생성하는 여러 증강 방법이 제안되었다. 하지만, 이미지, 문자 등의 훈련데이터와 달리, 인간 동작 인식을 행하는 합성곱 신경망의 생체신호 훈련데이터를 추가로 생성하는 증강 방법은 연구 문헌에서 찾아보기 어렵다. 본 연구에서는 합성곱 신경망에 기반한 인간 동작 인식을 위한 생체신호 훈련데이터를 생성하는 간편하지만, 효과적인 증강 방법을 제안한다. 본 연구의 제안된 증강 방법의 유용성은 추가로 생성된 생체신호 훈련데이터로 학습하여 합성곱 신경망이 인간 동작을 높은 정확도로 인식하는 것을 보임으로써 검증하였다.

• 대한기계학회논문집
• /
• 제16권7호
• /
• pp.1322-1331
• /
• 1992

본 연구에서는 Fig.3과 같은 다층 퍼셉트론을 사용하기로 한다. 그리고 위 에서 언급한 세가지점에서 다층퍼셉트론을 다시 살펴보아 해결하고자 하는 문제에 맞 도록 다층퍼셉트론을 개선시켜 보기로 한다. 따라서 본 연구의 목적은 제한조건을 갖는 문제를 풀기위한 새로운 형태의 다층퍼셉트론 설계 및 이에 적합한 학습규칙을 적용하여 보다 간단한 구조와 빠른 학습시간을 갖는 신경망을 구성하는데 있다.

• 전자공학회논문지CI
• /
• 제44권2호
• /
• pp.11-18
• /
• 2007

신경회로망의 학습에 널리 사용되고 있는 오차역전파 알고리즘은 최급하강법을 기초로 하고 있기 때문에 초기값에 따라서는 극소값에 떨어지거나, 신경회로망을 학습시킬 때 중간층 유닛수를 얼마로 설정하는 등의 문제점이 있다. 따라서 이러한 문제점을 해결하기 위하여, 본 논문에서는 3비트 패리티 판별을 위하여 신경회로망의 학습에 교차법, 돌연변이법에 새로운 기법을 도입한 개량형 유전적 알고리즘을 제안한다. 본 논문에서는 세대차이, 중간층 유닛수의 차이, 집단의 개체수의 차이에 대하여 실험을 실시하여, 본 방식이 학습 속도의 면에서 유효하다는 것을 나타낸다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1251-1254
• /
• 2003

In this paper, Experience Sensitive Cumulative Neural Network (ESCNN) is introduced, which can cumulate the same or similar experiences. As the same or similar training patterns are cumulated in the network, the system recognize more important information in the training patterns. The functions of forgetting less important informations and attending more important informations resided in the training patterns are surveyed and implemented by simulations. The system behaves well under the noisy circumstances due to its forgetting and/or attending properties, even in 50 percents noisy environments. This paper also describes the creation of the generalized patterns for the input training patterns.

• 한국정보기술학회 영문논문지
• /
• 제8권2호
• /
• pp.119-127
• /
• 2018

Training a very large deep neural network can be painfully slow and prone to overfitting. Many researches have done for overcoming the problem. In this paper, a combination of early stopping and ADAM based deep neural network was presented. This form of deep network is useful for handling the big data because it automatically stop the training before overfitting occurs. Also generalization ability is better than pure deep neural network model.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.77-87
• /
• 2021

In this study, a novel improved second order Radial Basis Function Neural Network based method with excellent scheduling capabilities is used for the dynamic prediction of short and long-term energy required applications. The effectiveness and the reliability of the algorithm are evaluated using training operations with New England-ISO database. The dynamic prediction algorithm is implemented in Matlab and the computation of mean absolute error and mean absolute percent error, and training time for the forecasted load, are determined. The results show the impact of temperature and other input parameters on the accuracy of solar Photovoltaic load forecasting. The mean absolute percent error is found to be between 1% to 3% and the training time is evaluated from 3s to 10s. The results are also compared with the previous studies, which show that this new method predicts short and long-term load better than sigmoidal neural network and bagged regression trees. The forecasted energy is found to be the nearest to the correct values as given by England ISO database, which shows that the method can be used reliably for short and long-term load forecasting of any electrical system.

• 한국생산제조학회지
• /
• 제6권1호
• /
• pp.27-33
• /
• 1997

A neural network approach has been developed to determine the depth of a surface breaking crack in a steel plate from ultrasonic backscattering data. The network is trained by the use of feedforward three-layered network together with a back-scattering algorithm for error correction. The signal used for crack insonification is a mode converted 70$^{\circ}$transverse wave. A numerical analysis of back scattered field is carried out based on elastic wave theory, by the use of the boundary element method. The numerical data are calibrated by comparison with experimental data. The numerical analysis provides synthetic data for the training of the network. The training data have been calculated for cracks with specified increments of the crack depth. The performance of the network has been tested on other synthetic data and experimental data which are different from the training data.