• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.213-217
• /
• 1990

Neural networks are a class of systems that have many simple processors (neurons) which are highly interconnected. The function of each neuron is simple, and the behavior is determined predominately by the set of interconnections. Thus, a neural network is a special form of parallel computer. Although a major impetus for using neural networks is that they may be able to "learn" the solution to the problem that they are to solve, we argue that another, perhaps even stronger, impetus is that they provide a framework for designing massively parallel machines. The highly interconnected architecture of switching networks suggests similarities to neural networks. Here, we present two switching applications in which neural networks can solve the problems efficiently. We also show that a computational advantage can be gained by using nonuniform time delays in the network.e network.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.27-34
• /
• 1996

GENIE is a learning-based engine for building intelligent systems. Learning in GENIE proceeds by incrementally modeling its human or technical environment using a neural network and a genetic algorithm. The neural network is used to represent the knowledge for solving a given task and has the ability to grow its structure. The genetic algorithm provides the neural network with training examples by actively exploring the example space of the problem. Integrated into the training examples by actively exploring the example space of the problem. Integrated into the GENIE system architecture, the genetic algorithm and the neural network build a virtually self-teaching autonomous learning system. This paper describes the structure of GENIE and its learning components. The performance is demonstrated on a robot learning problem. We also discuss the lessons learned from experiments with GENIE and point out further possibilities of effectively hybridizing genetic algorithms with neural networks and other softcomputing techniques.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.798-800
• /
• 1995

The neural network predictive controller(NNPC) is proposed for the attempt to mimic the function of brain that forecasts the future. It consists of two loops, one is for the prediction of output(Neural Network Predictor) and the other one is for control the plant(Neural Network Controller). The output of NNC makes the control input of plant, which is followed by the variation of both plant error and prediction error. The NNP forecasts the future output based upon the current control input and the estimated control output. The method is applied to the control of temperature in boiler systems. The proposed NNPC is compared with the other conventional control methods such as PID controller, neural network controller with specialized learning architecture, and one-step-ahead controller. The computer simulation and experimental results show that the proposed method has better performances than the other methods.

• 한국정보시스템학회:학술대회논문집
• /
• 한국정보시스템학회 1996년도 추계학술발표회 발표논문집
• /
• pp.211-216
• /
• 1996

This paper propose a fuzzy regression method using fuzzy neural networks when a membership value is attached to each input-output pair. First, an architecture o fuzzy neural networks with fuzzy weights and fuzzy biases is shown. Next, a cost function is defined using the fuzzy output from the fuzzy neural network and the corresponding target output with a membership value. A learning algorithm is derived from the cost function. The derived learning algorithm trains the fuzzy neural network so 솜 t the level set of the fuzzy output includes the target output. Last, the proposed method is applied to the quality evaluation problem of injection molding

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2008년도 추계학술발표논문집
• /
• pp.191-196
• /
• 2008

The intent of this paper is to describe a neural network structure called dynamic neural processor(DNP), and examine how it can be used in developing a learning scheme for computing robot inverse kinematic transformations. The architecture and learning algorithm of the proposed dynamic neural network structure, the DNP, are described. Computer simulations are provided to demonstrate the effectiveness of the proposed learning using the DNP.

• Transactions on Control, Automation and Systems Engineering
• /
• 제3권1호
• /
• pp.43-50
• /
• 2001

In this paper, we propose the design procedure of advance Polynomial Neural Networks(PNN) architecture for optimal model identification of complex and nonlinear system. The proposed PNN architecture is presented as the generic and advanced type. The essence of the design procedure dwells on the Group Method of Data Handling(GMDH). PNN is a flexible neural architecture whose structure is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated in a dynamic way. In this sense, PNN is a self-organizing network. With the aid of three representative numerical examples, compari-sons show that the proposed advanced PNN algorithm can produce the model with higher accuracy than previous other works. And performance index related to approximation and generalization capabilities of model is evaluated and also discussed.

• 한국인터넷방송통신학회논문지
• /
• 제22권3호
• /
• pp.69-74
• /
• 2022

뉴로모픽 아키텍처에서 동작하는 SNN (Spiking Neural Network) 은 인간의 신경망을 모방하여 만들어졌다. 뉴로모픽 아키텍처 기반의 뉴로모픽 컴퓨팅은 GPU를 이용한 딥러닝 기법보다 상대적으로 낮은 전력을 요구한다. 이와 같은 이유로 뉴로모픽 아키텍처를 이용하여 다양한 인공지능 모델을 지원하고자 하는 연구가 활발히 일어나고 있다. 본 논문에서는 음성 데이터 전처리 기법에 따른 뉴로모픽 아키텍처 기반의 음성 인식 모델의 성능 분석을 진행하였다. 실험 결과 푸리에 변환 기반 음성 데이터 전처리시 최대 84% 정도의 인식 정확도 성능을 보임을 확인하였다. 따라서 뉴로모픽 아키텍처 기반의 음성 인식 서비스가 효과적으로 활용될 수 있음을 확인하였다.

• 소성∙가공
• /
• 제4권3호
• /
• pp.214-221
• /
• 1995

In the paper, we have proposed a new method to determine the initial billet for the forged products using a function approximation in the neural network. The architecture of neural network is a three-layer neural network and the back propagation algorithm is employed to train the network. By utilizing the ability of function approximation of a neural network, an optimal billet is determined by applying the nonlinear mathematical relationship between the aspect ratios in the initial billet and the final products. The amount of incomplete filling in the die is measured by the rigid-plastic finite element method. The neural network is trained with the initial billet aspect ratios and those of the unfilled volumes. After learning, the system is able to predict the filling regions which are exactly the same or slightly different to the results of finite element simulation. This new method is applied to find the optimal billet size for the plane strain rib-web product in cold forging. This would reduce the number of finite element simulation for determining the optimal billet size of forging product, further it is usefully adapted to physical modeling for the forging design.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1999년도 학술발표대회 논문집 제18권 1호
• /
• pp.78-81
• /
• 1999

본 논문에서는 인간의 정보처리 기술을 모방한 신경망과 한국어 음절 구성의 특성을 이용하여 음절을 기반으로 하는 신경망 음성인식 방법을 제안한다. 제안한 방법에서는 임계비율을 정의하여 한국어 음절을 구성하는 초성$\cdot$중성$\cdot$종성을 구분하였고, 구분된 음절의 일부 구간 특징을 학습 및 인식의 특징 패턴으로 사용하여 음성인식 시스템의 전체적인 처리 단계를 줄였다. 한국어 숫자음 인식에 대한 성능 평가에서 20대 남성과 여성을 대상으로 화자 종속에서 $96.5\%$의 인식률을 화자 독립에서 $93\%$의 인식률을 얻었다.

• 제어로봇시스템학회논문지
• /
• 제11권3호
• /
• pp.233-239
• /
• 2005

This paper presents the design and evaluation of a tiltrotor attitude controller. The implemented response type of the command augumentation system is Attitude Command Attitude Hold. The controller architecture can alleviate the need for extensive gain scheduling and thus has the potential to reduce development time. The control algorithm is constructed using the feedback linearization technique. And an on-line adaptive architecture that employs a neural network compensating the model inversion error caused by the deficiency of full knowledge tiltrotor aircraft dynamics is applied to augment the attitude control system. The use of Lyapunov stability analysis guarantees boundedness of the tracking error and network parameters. The performance of the controller is evaluated against ADS-33E criteria, using the nonlinear tiltrotor simulation code for Bell TR301 developed by KARI. (Korea Aerospace Research Institute)