• The Korean Journal of Applied Statistics
• /
• v.12 no.2
• /
• pp.505-515
• /
• 1999

인공신경망 모형을 적합시키는데 사용하는 역전파 알고리즘을 로버스트하게 만드는 새로운 오차함수를 제안했으며, 새 방법의 성능을 확인하기 위해 Liano가 제안한 방법에 따라 모의실험을 수행했다. 실험결과 새 방법은 LMS방법만큼 안정적이었으며, Liano의 LMLS방법보다 더 로버스트했다. 또 실제 사례를 분석함으로써 이 방법이 의미있는 방법임을 보였다. 새 방법은 특히 오차가 없거나 작은 오차를 갖는 표본에 대해서도 좋은 성질을 가짐으로서 대형오차의 유무에 관계없이 항상 사용할 수 있는 방법으로 판명되었다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.315-317
• /
• 2003

Neural oscillator is applied in oscillatory systems (Analysis of image information, Voice recognition. Etc...). If we apply established EBPA(Error back Propagation Algorithm) to oscillatory system, we are difficult to presume complicated input's patterns. Therefore, it requires more data at training, and approximation of convergent speed is difficult. In this paper, I studied the neural oscillator as synchronized states with appropriate phase relation between neurons and recognized the Korean alphabet using Neural Oscillator Phase model Synchronization.

• Journal of Advanced Marine Engineering and Technology
• /
• v.18 no.5
• /
• pp.36-45
• /
• 1994

This paper describes how to identify standard numbers and to diagnose defects of the ball bearings. The first stage of the networks is a procedures for identifying standard numbers of the bearings, and the next stage carries out the diagnosis of defects on the outer race and the inner race of bearings. The identification and the diagnosis of bearings were carried out by simulations and experiments.

• Korean Journal of Biological Psychiatry
• /
• v.4 no.2
• /
• pp.194-197
• /
• 1997

Neural network models, also known as connectionist models or PDP models, simulate some functions of the brain and may promise to give insight in understanding the cognitive brain functions. The models composed of neuron-like elements that are linked into circuits can learn and adapt to its environment in a trial and error fashion. In this article, the history and principles of the neural network modeling are briefly reviewed, and its applications to psychiatry are discussed.

• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.457-460
• /
• 1989

In this paper, an improvement of the EBP(error back propagation) learning speed using an acceleration algorithm is described. Using an acceleration algorithm known as the Partan method in the gradient search algorithm, learning speed is 25% faster than the original EBP algorithm in the simulaion results.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.102.2-102
• /
• 2002

In this paper, the improved Multi-FNN (Fuzzy-Neural Networks) model is identified and optimized using HCM (Hard C-Means) clustering method and optimization algorithms. The proposed Multi-FNN is based on FNN and use simplified and linear inference as fuzzy inference method and error back propagation algorithm as learning rules. We use a HCM clustering and genetic algorithms (GAs) to identify both the structure and the parameters of a Multi-FNN model. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNN according to the divisions of input-output space using I/O process data. Also, the parame...

• Proceedings of the Optical Society of Korea Conference
• /
• 1995.06a
• /
• pp.117-120
• /
• 1995

분수차 퓨리에(Fouier) 변환은 퓨리에 면환을 일반화시킨 것으로, 위치와 공간주파수의 복합적인 표현을 주나, 한 개의 렌즈를 광학적 구현이 역시 가능하다. 광신호처리에서 많이 사용되는 정합 필터를 구성하는 퓨리에 면환을 각각 분수차로 일반화시킴으로서, 위치 필터와 공간주파수 필터의 특성이 복합된 새로운 필터를 구성할 수 있게 된다. 이 필터 구조는 신경회로망의 학습으로 대치된다. 최대경사법과 오차역전파(error back-propagation)에 기초한 학습 법칙이 유도되고, 컴퓨터 시뮬레이션 결과가 제시된다.

• Journal of Biomedical Engineering Research
• /
• v.12 no.3
• /
• pp.191-202
• /
• 1991

This paper describes ECG data compression algorithm using neural network. As a learning method, we use back error propagation algorithm. ECG data compression is performed using learning ability of neural network. CSE database, which is sampled 12bit digitized at 500samp1e/sec, is selected as a input signal. In order to reduce unit number of input layer, we modify sampling ratio 250samples/sec in QRS complex, 125samples/sec in P & T wave respectively. hs a input pattern of neural network, from 35 points backward to 45 points forward sample Points of R peak are used.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.49-52
• /
• 1998

Neural Network has good performance in pattern classification, control and many other fields by learning ability. However, there is effective rule or systematic approach to determine optimal structure. In this paper, we propose a new method to find optimal structure of feed-forward multi-layer neural network as a kind of pruning method. That eliminating redundant elements of neural network. To find redundant elements we analysis error and weight changing with Rough Set Theory, in condition of executing back-propagation leaning algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.118-121
• /
• 2000

본 논문에서는 FNNs(feedforwad neural networks)구현을 위한 새로운 학습 방안을 제안하였다. 제안된 방식은 온 칩 학습이 가능하도록 FNNs와 학습회로 사이에 스위칭 회로를 추가하여 단일패턴과 다중패턴 학습이 가능하도록 구현하였다. 학습 회로는 MEBP(modified error back-propagation) 학습 규칙을 적용하였고 간단한 비선형 시냅스 회로를 이용하여 구현하였다. 제안된 방식은 표준 CMOS 공정으로 구현되었고, MOSIS AMI $1.5\mu\textrm{m}$공정 HSPICE 파라메터를 이용하여 그 동작을 검증하였다. 제안된 학습방안 및 비선형 회로는 향후 학습 기능을 가진 대규모의 FNNs 구현에 매우 적합하리라 예상된다.