• The Journal of Information Technology
• /
• v.7 no.3
• /
• pp.11-18
• /
• 2004

Learning procedure in the neural network is updating of weights between neurons. Unadequate initial learning coefficient causes excessive iterations of learning process or incorrect learning results and degrades learning efficiency. In this paper, adaptive learning algorithm is proposed to increase the efficient in the learning algorithms of Self-Organization Neural Networks. The algorithm updates the weights adaptively when learning procedure runs. To prove the efficiency the algorithm is experimented to classification of strokes which is the reference handwritten character. The result shows improved classification rate about 1.44~3.65% proposed method compare with Kohonan and Mao's algorithms, in this paper.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.330-340
• /
• 1998

자율주행 반송차가 주어진 경로를 따라 주행 할 때 주행면의 불균일성과 같은 외란요인과 자율반송차 시스템 자체의 비선형성 등으로 인하여 원치 않는 경로추종오차가 발생하게 되는데 본 연구에서는 이러한 경로추종오차를 최소화하기 위해서 신경회로망을 이용한 경로추종 오차 보상방법을 제안한다. 본 방법에서는 신경회로망을 통하여 조향각 보상량을 제공하므로써 경로추종오차를 보상한다. 신경망은 다층 퍼셉트론을 채용하였으며 역전파 알고리즘의 최급강하규칙(Gradient descent rule)을 이용하여 학습을 수행하였다. 본 제안에서는 학습오차를 경로추종오차로부터 정의하므로써 경로추종오차가 최소화되록 신경회로망을 학습시켰다. 제안된 방법의 타당성은 다양한 경로에 대한 모의실험 및 실제 실험을 통하여 검증하였다.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.2
• /
• pp.66-75
• /
• 2002

This paper presents an adaptive back propagation algorithm that its able to enhancement for the learning efficiency with updating the learning parameter and varies the number of hidden layer node by the generated error, adaptively. This algorithm is expected to escaping from the local minimum and make the best environment for the convergence of the back propagation neural network. On the simulation tested this algorithm on three learning pattern. One was exclusive-OR learning and the another was 3-parity problem and 7${\times}$5 dot alphabetic font learning. In result that the probability of becoming trapped in local minimum was reduce. Furthermore, the neural network enhanced to learning efficient about 17.6%~64.7% for the existed back propagation. 

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.3
• /
• pp.270-279
• /
• 2000

This paper describes the on-chip learning algorithm of neural networks using the stochastic pulse arithmetic. Stochastic pulse arithmetic is the computation using the numbers represented by the probability of 1' and 0's occurrences in a random pulse stream. This stochastic arithmetic has the merits when applied to neural network ; reduction of the area of the implemented hardware and getting a global solution escaping from local minima by virtue of the stochastic characteristics. And in this study, the on-chip learning algorithm is derived from the backpropagation algorithm for effective hardware implementation. We simulate the nonlinear separation problem of the some character patterns to verify the proposed learning algorithm. We also had good results after applying this algorithm to recognize printed and handwritten numbers.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.11
• /
• pp.1201-1209
• /
• 1991

Generally, the conventional tracking algorithms are very limited in the practical applications because of its exponential increase in the required computation time for the number of targets being tracked. Therefore, in this paper, a new real-time moving target tracking system is proposed, which is based on the neural networks with massive parallel processing capabilities. Through the theoretical and experimental results, the target tracking system based on neural network algorithm is analyzed to be computationally independent of the number of objects being tracked and performs the optimized tracking through its massive parallel computation and learning capabilities. And this system also has massive matched filtering effects because the moving target data can be compactly stored in the interconnection weights by learning. Accordingly, a possibility of the proposed neural network target tracking system can be suggested to the fields of real-time application.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.4
• /
• pp.382-387
• /
• 1998

The adaptive hysteresis band current control method using neural network is proposed to hold the switching frequency of PWM inverter constant at any operating points of ac motor. The adaptive hysteresis band equation is derived as the teaching signal of neural network. and then the structure and learning algorithm of the neural network a are suggested. The simulation results show that the switching frequency of PWM inverter is held constant at any operating conditions of ac motor and the proposed method has good transient performance of stator current.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2002.05a
• /
• pp.215-220
• /
• 2002

본 연구에서는 다중채널 뇌파에서 특징 파라미터로 선형 예측기 계수(Linear predictor coefficients)를 추출하고, 패턴인식기로는 신경회로망을 이용한 쾌적성 분류 알고리즘을 개발하여 다중 템플릿 방법으로 쾌적성 분류 실험을 하고자 하였다. 뇌파 데이터는 대학생 10명으로부터 쾌적한 환경과 불쾌적한 환경에서의 데이터를 수집하였으며, 전극 위치는 Fpl, Fp2, F3, F4, T3, T4, P3, P4, O1, O2를 사용하였다. 수집된 뇌파는 전처리를 거친 후 특징 파라미터를 추출하고 패턴 분류기로 사용된 신경회로망의 입력으로 사용하였다. 쾌적성 분류 방법은 다중템플릿 방법으로 여러 명의 피검자를 각각 학습시켜 이로부터 생성되는 신경회로망의 가중치들을 템플릿에 저장한다. 그리고 테스트를 할 때에는 먼저 처음의 안정 상태의 뇌파를 이용하여 템플릿 검색을 하고 가장 가까운 템플릿을 선택한다. 그리고 선택된 템플릿을 이용하여 다른 감정에 대한 쾌적성 분류 실험을 하게 된다. 쾌적성 분류 실험 결과 평균 인식률이 약 75%의 성능을 나타내었다.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.11 no.1
• /
• pp.39-47
• /
• 1997

본 논문에서는 퍼지제어기와 신경회로망 적응 관측기를 적용하여 강인성을 AC드라이브 시스템을 제안하였다. 퍼지제어기는 유도전동기의 속도 제어시 빠른 속도 응답 특성을 얻기 위하여 사용하였다. 신경회로망 적응관측기는 전동기 파라메터 변화에 대하여 강인한 제어 시스템이 되도옥 자속 관측기오 토오크 적응관측기로 구성하였다. 사용된 신경회로망은 자속과 토오크의 동특성을 학습시키기 위하여 역전파 알고리즘을 사용하였따. 컴퓨터 시뮬레이션의 결과를 통해 제안된 시스템이 전동기 파라메터 변동과 부화이론에 강인하고 속도응답 특성이 우수함을 입증하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.11a
• /
• pp.155-158
• /
• 1998

다층 신경회로망의 모델의 크기는 적용분야에 따라서 임의로 선택되어지고, 최적의 네트워크 크기는 긴 시간에 걸친 시행착오를 통하여 결정된다. 본 논문에서는 은닉충의 뉴런 수를 학습 과정에서 유동적으로 결정하는 역전파 알고리즘을 제안한다. 기존의 Narendra의 모델의 동정에 대하여 제안한 알고리즘의 유용성을 비교 검토하였다.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.271-276
• /
• 2003

In this study, we compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as shape recognition algorithm of welding flaws. For this purpose, variables are applied the same to two algorithm. Here, feature variable is composed of time domain signal itself and frequency domain signal itself, Through this process, we comfirmed advantages/disadvantages of two algorithms and identified application methods of two algorithms.