• 전자공학회논문지B
• /
• 제31B권12호
• /
• pp.116-123
• /
• 1994

A modified Hybrid learning rule(MHLR) is proposed, which is derived from combining the Back Propagation algorithm that is known as an excellent classifier with modified Hebbian by changing the orginal Hebbian which is a good feature extractor. The network architecture of MHLR is multi-layered neural network. The weights of MHLR are calculated from sum of the weight of BP and the weight of modified Hebbian between input layer and higgen layer and from the weight of BP between gidden layer and output layer. To evaluate the performance, BP, MHLR and the proposed Hybrid learning rule (HLR) are simulated by Monte Carlo method. As the result, MHLR is the best in recognition rate and HLR is the second. In learning speed, HLR and MHLR are much the same, while BP is relatively slow.

• 한국음향학회지
• /
• 제13권4호
• /
• pp.60-68
• /
• 1994

본 논문에서는 다층구조 순방향 신경회로망에 적용될 수 있는 것으로 입력의 특징 추출기능(Feature Extractor)이 우수한 Hebb 학습 규칙과 패턴 분류 기능(Classifier)이 우수한 BP 알고리듬을 결합한 Hybrid학습 규칙을 제안하고자 한다. 오차역전파 학습법칙을 적용한 다층구조퍼셉트론(MLP)과는 달리, 다층구조에 오차역전파 학습법칙과 Hebb학습법칙이 동시에 적용될 수 있는 Hybrid(Hebbian+BP)학습법칙은 학습시에 출력층의 연결강도를 제외한 모든 연결강도 계산에 적용되며 출력층에는 기존의 오차역전파법칙만이 적용된다. 출력층에 Hebb 학습법칙을 제외시킨것은 다층구조학습시에 학습의 수렴성에 대한 보장이 주어져 있지 않기 때문이다. 제안된 Hybrid 학습법칙의 성능평가를 위해 몇가지의 영역구분 문제에 적용한 결과 제안된 학습법이 기존의 BP보다 우수함을 보였다. 학습속도면에서는 기존의 BP법칙에 비해 훨씬 빠른 수렴속도를 보여 주었는데, 그중 한가지 예를 보면 제안된 Hybrid법칙에 의한 학습은 기존의 BP의 학습회수의 2/10만으로도 가능함을 보여주었다. 인식률에서도 제안된 법칙에 의한 결과가 BP에 의한 결과보다 최고 약 $0.77\%$ 우수하다.

• 전자공학회논문지B
• /
• 제31B권8호
• /
• pp.211-218
• /
• 1994

In this paper we develope a hybrid learning rule to improve the robustness of multi-layer Perceptions. In most neural networks the activation of a neuron is deternined by a nonlinear transformation of the weighted sum of inputs to the neurons. Investigating the behaviour of activations of hidden layer neurons a new learning algorithm is developed for improved robustness for multi-layer Perceptrons. Unlike other methods which reduce the network complexity by putting restrictions on synaptic weights our method based on error-backpropagation increases the complexity of the underlying proplem by imposing it saturation requirement on hidden layer neurons. We also found that the additional gradient-descent term for the requirement corresponds to the Hebbian rule and our algorithm incorporates the Hebbian learning rule into the error back-propagation rule. Computer simulation demonstrates fast learning convergence as well as improved robustness for classification and hetero-association of patterns.

• Journal of the Korean Data and Information Science Society
• /
• 제7권2호
• /
• pp.203-210
• /
• 1996

A linear neural unit with a modified anti-Hebbian learning rule has been shown to be able to optimally fit curves, surfaces, and hypersurfaces by adaptively extracting the minor component of the input data set. In this paper, we study how to use the robust version of this neural fitting method for linear regression analysis. Furthermore, we compare this method with other methods when data set is contaminated by outliers.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.491-494
• /
• 2004

Neural Oscillator can be applied to oscillatory systems such as the image recognition, the voice recognition, estimate of the weather fluctuation and analysis of geological fluctuation etc in nature and principally, it is used often to pattern recoglition of image information. Conventional BPL(Back-Propagation Learning) and MLNN(Multi Layer Neural Network) are not proper for oscillatory systems because these algorithm complicate Learning structure, have tedious procedures and sluggish convergence problem. However, these problems can be easily solved by using a synchrony characteristic of neural oscillator with PLL(phase-Locked Loop) function and by using a simple Hebbian learning rule. And also, Recognition velocity of Korean Character can be improved by using a Neural Oscillator's learning accelerator factor η$\_$ij/

• Journal of Advanced Marine Engineering and Technology
• /
• 제28권2호
• /
• pp.347-353
• /
• 2004

Neural oscillator can be applied to oscillator systems such as analysis of image information, voice recognition and etc, Conventional learning algorithms(Neural Network or EBPA(Error Back Propagation Algorithm)) are not proper for oscillatory systems with the complicate input patterns because of its too much complex structure. However, these problems can be easily solved by using a synchrony characteristic of neural oscillator with PLL(phase locked loop) function and a simple Hebbian learning rule, Therefore, in this paper, it will introduce an technique for Recognition of the Korean Character using Phase Synchronization Neural Oscillator and will show the result of simulation.

• 한국지능시스템학회논문지
• /
• 제14권1호
• /
• pp.93-99
• /
• 2004

Neural oscillator can be applied to oscillatory systems such as analyses of image information, voice recognition and etc. Conventional EBPA (Error back Propagation Algorithm) is not proper for oscillatory systems with the complicate input`s patterns because of its tedious training procedures and sluggish convergence problems. However, these problems can be easily solved by using a synchrony characteristic of neural oscillator with PLL(Phase Locked Loop) function and by using a simple Hebbian learning rule. Therefore, in this paper, a technique for Recognition of the Korean Alphabet using Phase Synchronized Neural Oscillator was introduced.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.115.3-115
• /
• 2001

In this paper, discrete-time cellular neural networks are designed in order to function as associative memories by using Hebbian learning rule and non-cloning template. The proposed method has a very simple structure to design and to learn. Weights are updated by the connection between the neuron and its neighborhood. In the simulation, the proposed method is applied to the classification of a traffic sign pattern.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
• /
• pp.333-335
• /
• 1998

에러 역전파 신경망에서 학습속도와 수렴률은 초기 가중의 분포에 따라 크게 영향을 받는다. 본 연구에서는 이를 위하여 비교사 학습 신경망(Hebbian learning rule)을 이용한 새로운 초기 가중치 결정 방법을 제안한다. 또는 비교사 학습 신경망이 에러 역전파 신경망 학습에 적당하도록 은닉층의 각 뉴런과 연결된 가중치의 norm을 이용하여 학습하였다. 시뮬레이션을 통하여 기존 에러 역전파 신경망 학습과 그 성능을 비교한 결과 제안한 초기 가중치 표현이 학습속도와 수렴능력에서 우수함을 나타낸다.

• Journal of the Korean Data and Information Science Society
• /
• 제7권1호
• /
• pp.113-118
• /
• 1996

주성분 분석은 자료압축, 특징추출, 통신이론, 패턴인식 그리고 화상처리등의 컴퓨터 공학분야에서 중요하게 사용되고 있다. Oja(1982,1989,1992)는 확률적 경사 강하법(SGA:Stochastic Gradient Ascent)을 이용한 제한된 헵규칙을 제안하여 주성분 분석에 사용하였다. 그러나, 이 규칙은 이상치에 민감하므로 이상치의 영향을 줄이기 위해, Xu & Yuille(1995)는 통계물리 방법을 이용한 로버스트 에너지함수를 생성하여 로버스트 주성분 분석방법을 제안하였다. 또한 Devlin et.al(1981)은 M-추정량을 이용하여 주성분 분석을 하였다. 본 논문에서는 Oja(1992)의 규칙과 Xu & Yuille(1995)의 로버스트 에너지함수를 이용하여 신경망을 구성하였다. 그리고, Devlin et.al(1981)이 제안한 시뮬레이션조건하에서 실험을 하였다. 실험한 결과와 Devlin et.al(1981)의 결과를 비교, 분석함으로써, 신경망의 성능을 확인하고자 한다.