• 한국정보통신학회논문지
• /
• 제2권1호
• /
• pp.157-163
• /
• 1998

아날로그와 디지틀 합산 가능한 신경회로망회로를 제안한다. 제안된 회로는 Hopfield 신경회로망 모델을 사용하였으며, 연결강도들은 에너지함수를 이용해서 구하였다. NMOS를 이용하여 뉴론을 만들었고, 시뮬레이션결과는 거의 대부분의 경우가 전체 최소점으로 수렴함을 보였다.

• 대한전자공학회논문지
• /
• 제26권10호
• /
• pp.1576-1583
• /
• 1989

In this paper, we describe real-time optical implementation of the Hopfield neural network model for two-dimensional associative memory by using commercial LCTV and Multifocus For real-time processing capability, we use LCTV as a memory mask and a input spatial light modulator. Inner product between input pattern and memory matrix is processed by the multifocus holographic lens. The output signal is then electrically thresholded fed back to the system input by 2-D CCD camera. From the good experimental results, the proposed system can be applied to pattern recognition and machine vision in future.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.726-730
• /
• 1990

In this paper, assuming that local range information is available, a collision-free path planning algorithm for multiple mobile robots is presented by using Hopfield neural optimization network. The energy function of the network is built using the present position and the goal position of each robot as well as its local range information. The proposed algorithm has several advantages such as the effective passing around obstacles with the directional safety distance, the easy implementation of robot motion planning including its rotation, the real-time path planning capability from the totally localized computations of path for each robot, and the adaptivity on arbitrary environment since any special shape of obstacles is not assumed.

• 한국통신학회논문지
• /
• 제30권2B호
• /
• pp.21-26
• /
• 2005

효율적인 통신망에서의 라우팅을 위해, 개선된 에너지 함수를 가지는 Hopfield 신경망에 의한 알고리즘이 본 논문에서 제안되었는데, 보다 높은 최적경로 형성과 안정적 수렴의 결과를 목적으로 한다. 20-50 개의 노드를 가지며, 무작위 연결 비용이 인가되는 3,000 개의 통신망에 대한 실험의 결과에서 볼 때, 기존의 신경망을 이용한 알고리즘들이 노드 수가 많은 망 환경에서 수렴하지 않거나, 최적경로가 형성이 되지 않은 경우가 많았지만 제안된 알고리즘은 최적경로 형성에서 기존 알고리즘 보다 약 65%의 개선을 하였고 또한 기존 알고리즘 보다 약 50% 정도 수렴이 잘 되는 것이 확인되었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1037-1041
• /
• 1996

Input-output linearization technique in nonlinear control does not guarantee the robustness in the presence of parameter uncertainty or unmodeled dynamics, etc. However, it has been used as an important preliminary step in achieving additional control objectives, for instance, robustness to parameter uncertainty and disturbance attenuation. An indirect adaptive control scheme based on input-output linearization is proposed in this paper. The scheme consists of a Hopfield network for process parameter identification and an adaptive sliding mode controller based on input-output linearization, which steers the system response into a desired configuration. A numerical example is presented for the trajectory tracking of uncertain nonlinear dynamic systems with slowly time-varying parameters.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.169.5-169
• /
• 2001

This study proposes a neural network for solving optimization problems such as the TSP (Travelling Salesman Problem), scheduling, and line balancing. The Hopfield network has been used for solving such problems, but it frequently gives abnormal solutions or non-optimal ones. Moreover, the Hopfield network takes much time especially in solving large size problems. To overcome such disadvantages, this study adopts nodes whose outputs changes with a fixed value at every evolution. The proposed network is applied to solving a TSP, finding the shortest path for visiting all the cities, each of which is visted only once. Here, the travelling path is reflected to the energy function of the network. The proposed network evolves to globally minimize the energy function, and a ...

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 추계학술대회 논문집 학회본부
• /
• pp.189-192
• /
• 1991

This paper presents a modular structure design of analog Hopfield neural network. Each multiplier consists of four MOS transistors which are connected to an op-amp at the front end of a neuron. A pair of MOS transistor is used in order to maintain linear operation of the synapse and can produce positive or negative synaptic weight. This architecture can be expandable to any size neural network by forming tree structure. By altering the connections, other nework paradigms can also be implemented using this basic modules. The stength of this approach is the expandability and the general applicability. The layout design of a four-neuron fully connected feedback neural network is presented and is simulated using SPICE. The network shows correct retrival of distorted patterns.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국제학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.391-394
• /
• 1993

A new approach using a Hopfield type neural network to solve line balancing problems for manufacturing planning is proposed. The energy function of the network to evaluate solutions is composed of three terms;(a) an operation should be processed at one and only one workstation, (b) the precedence-relationship between two operations shoud be satisfied, and (c) the cycle-time of operations should be minimized. It is shown that the network can solve the line balancing problems but not always because of the difficulty to keep the precedence-relationship. Therefore, a method to keep the precedence-relationship by software logic is proposed and it is verified that the line-balancing prblems can be solved with high probability.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1996년도 추계학술발표회논문집(1)
• /
• pp.21-26
• /
• 1996

The identification of radioactive source in a medium with a limited number of external detectors is introduced as an inverse radiation transport problem. This kind of inverse problem is usually ill-posed and severely under-determined, however, its applications are very useful in manu fields including medical diagnosis and nondestructive assay of nuclear materials. Therefore, it is desired to develop efficient and robust solution algorithms. As an approach to solving inverse problems, an artificial neural network is proposed. We develop a modified version of the conventional Hopfield neural network and demonstrate its efficiency and robustness.

• Journal of Welding and Joining
• /
• 제18권3호
• /
• pp.114-121
• /
• 2000

Since resistance spot welding has become one of the most popular sheet metal fabrication processes, a strong emphasis is being put on the quality of the welds. Throughout the years many quality estimation systems have been developed by many researchers to ensure weld quality. In this study, the process variables, which were monitored in the primary circuit of the welding machine, are used to estimate the weld quality with Hopfield neural network. The primary dynamic resistance is vectorized and stored as five patterns in the network. As the welding is done, the dynamic resistance patterns are recognized and the quality is estimated with the proposed method. Due to the primary process variables, it is possible to utilize this algorithms as an in-process real time quality monitoring system.