• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1565-1568
• /
• 2003

In this paper, we propose modular network to solve difficult and complex problems that are seldom solved with multi-layer neural network. The structure of modular neural network in researched by Jacobs and Jordan is selected in this paper. Modular network consists of several expert networks and a gating network which is composed of single-layer neural network or multi-layer neural network. We propose modular network structure using recurrent neural network, since the state of the whole network at a particular time depends on an aggregate of previous states as well as on the current input. Finally, we show excellence of the proposed network compared with modular network.

• 한국산림과학회지
• /
• 제84권1호
• /
• pp.63-70
• /
• 1995

이 논문에서는 neural network기법에 의해 소규모 임분의 시업계획을 분석하는 방법과 적용성을 평가하였다. 이를 위해서 적정한 임분시업체계를 계산하기 위한 neural network 모델을 개발하고, neural network의 구조체계와 network을 교육시키기 위해 요구되는 자료량의 측면에서 적용성을 검토하였다. 연구목적상 모델의 교육 및 비교분석에 요구되는 적정 시업체계에 대한 자료는 기존의 비선형 시업체계분석모델을 이용하였다. 이 시업체계 분석모델은 동령급 구조의 긴잎 소나무(Pinus palustris) 단순림의 적정시업체계를 분석하는 모델로서 전림수확생장함수에 의해 임분의 생장이 예측되는 모델이다. neural network 모델의 적용성 검토에 요구되는 분석자료들은 이 비선형 시업체계분석모델에 의해 제시된 긴잎소나무 임분의 적정 시업체제분석 결과들을 이용하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 춘계학술발표대회
• /
• pp.16-18
• /
• 2018

최근 네트워크 상에 새롭고 다양한 어플리케이션들이 생겨나면서 이에 따른 적절한 어플리케이션별 서비스 제공을 위한 패킷 분류 방법이 요구되고 있다. 이로 인하여 딥 러닝 기술이 발전 하면서 이를 이용한 네트워크 트래픽 분류 방법들이 제안되고 있다. 따라서, 본 논문에서는 딥 러닝 기술 중 Convolution Neural Network 와 Recurrent Neural Network 를 동시에 활용한 네트워크 패킷 분류 방법을 제안한다.

• 전자공학회논문지B
• /
• 제33B권11호
• /
• pp.127-139
• /
• 1996

In this paper we propose a new controller design method using hybrid fuzzy-neural netowrk and neural network identification in order ot control systems which are more and more getting nonlinearity. Proposed method performs, for a nonlinear plant with unknown functions, hybird identification using a fuzzy-neural network and a neural network, and then a stable nonlinear controller is designed with those identified informations. To identify a nonlinear function, which is directly related to input signals, we can use a neural network which is satisfied with the proposed stable condition. To identify a nonlinear function, which is not directly related to input signals, we can use a fuzzy-neural network which has excellent identification characteristics. In order to verify excellent control performances of the proposed method, we compare the porposed control method with a conventional neural network control method through simulations and experiments with one link manipulator.

• 한국통신학회논문지
• /
• 제17권5호
• /
• pp.482-494
• /
• 1992

In this paper, the neuro-fuzzy inferene system for the effective object recognition is studied. The proposed neuro-fuzzy inference system combines learning capability of neural network with inference process of fuzzy theory, and the system executes the fuzzy inference by neural network automatically. The proposed system consists of the antecedence neural network, the consequent neural network, and the fuzzy operational part, For dissolving the ambiguity of recognition due to input variance in the neuro-fuzzy inference system, the antecedence’s fuzzy proposition of the inference rules are automatically produced by error back propagation learining rule. Therefore, when the fuzzy inference is made, the shape of membership functions os adaptively modified according to the variation. The antecedence neural netwerk constructs a separated MNN(Model Classification Neural Network)and LNN(Line segment Classification Neural Networks)for dissolving the degradation of recognition rate. The antecedence neural network can overcome the limitation of boundary decisoion characteristics of nrural network due to the similarity of extracted features. The increased recognition rate is gained by the consequent neural network which is designed to learn inference rules for the effective system output.

• Journal of Mechanical Science and Technology
• /
• 제20권7호
• /
• pp.917-928
• /
• 2006

In recent decades, Artificial Neural Networks (ANNs) have become the focus of considerable attention in many disciplines, including robot control, where they can be used to solve nonlinear control problems. One of these ANNs applications is that of the inverse kinematic problem, which is important in robot path planning. In this paper, a neural network is employed to analyse of inverse kinematics of PUMA 560 type robot. The neural network is designed to find exact kinematics of the robot. The neural network is a feedforward neural network (FNN). The FNN is trained with different types of learning algorithm for designing exact inverse model of the robot. The Unimation PUMA 560 is a robot with six degrees of freedom and rotational joints. Inverse neural network model of the robot is trained with different learning algorithms for finding exact model of the robot. From the simulation results, the proposed neural network has superior performance for modelling complex robot's kinematics.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2003년도 추계학술대회
• /
• pp.57-72
• /
• 2003

This article provides integrated neural network models for the interest rate forecasting using change-point detection. The model is composed of three phases. The first phase is to detect successive structural changes in interest rate dataset. The second phase is to forecast change-point group with data mining classifiers. The final phase is to forecast the interest rate with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the predictability of integrated neural network models to represent the structural change.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.171-174
• /
• 2003

In this paper, a Learning module for a reconfigurable neural network processor(ERNIE) was proposed for an On-chip learning. The existing reconfigurable neural network processor(ERNIE) has a much better performance than the software program but it doesn't support On-chip learning function. A learning module which is based on Back Propagation algorithm was designed for a help of this weak point. A pipeline structure let the learning module be able to update the weights rapidly and continuously. It was tested with five types of alphabet font to evaluate learning module. It compared with C programed neural network model on PC in calculation speed and correctness of recognition. As a result of this experiment, it can be found that the neural network processor(ERNIE) with learning module decrease the neural network training time efficiently at the same recognition rate compared with software computing based neural network model. This On-chip learning module showed that the reconfigurable neural network processor(ERNIE) could be a evolvable neural network processor which can fine the optimal configuration of network by itself.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.142-145
• /
• 1997

This paper presents an modified orthogonal neural network(MONN) based on orthogonal functions and applies the network to nonlinear system control. The accuracy of orthogonal neural network is essentially dependent on the choice of basic orthogonal functions. Modified orthogonal neural network is modified model of orthogonal neural network with input transformation to adapt its basic orthogonal functions. The results show that the modified orthogonal neural network has the excellent performance of approximating and controlling nonlinear systems and the input transformation make the ability of modified orthogoneural neural network better than one of orthogonal neural network.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 춘계학술대회
• /
• pp.335-338
• /
• 2017

현재 인공지능과 딥 러닝이 사회적인 이슈로 떠오르고 있는 추세이며, 다양한 분야에 이 기술들을 응용하고 있다. 인공지능 분야의 여러 알고리즘들 중에서 각광받는 방법 중 하나는 Convolutional Neural Network이다. Convolutional Neural Network는 일반적인 Neural Network 방법에 Convolution 연산을 하여 Feature를 추출하는 Convolution Layer를 추가한 형태이다. Convolutional Neural Network를 적은 양의 데이터에서 이용하거나, Layer의 구조가 복잡하지 않은 경우에는 학습시간이 길지 않아 속도에 크게 신경 쓰지 않아도 되지만, 학습 데이터의 크기가 크고, Layer의 구조가 복잡할수록 학습 시간이 상당히 오래 걸린다. 이로 인해 GPU를 이용하여 병렬처리를 하는 방법을 많이 사용하는데, 본 논문에서는 CUDA를 이용한 Convolutional Neural Network를 구현하였으며, CPU를 이용한 방법보다 학습 속도가 빨라지고 큰 데이터를 학습 시키는데 더욱 효율적으로 진행하도록 한다.