• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1990년도 하계학술대회 논문집
• /
• pp.539-541
• /
• 1990

Hopfield crossbar assosiative network을 기초로한 개선된 Hopfield neural network을 제안하고, 이 network이 NP-complete 문제에 대한 효과적인 tool임을 보였다. 이 모델을 YLSI routing을 위한 layer assignment 문제에 응용하였고, 결과 이 개선된 Hopfield model이 stability와 accuracy를 향상시킴을 보여 주었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.160-160
• /
• 2000

An optimization approach is used to solve the division problem of working area, and a cost function is defined to represent the constraints on the solution, which is then mapped onto the Hopfield neural network for minimization. Each neuron in the network represents a possible combination among many components. Division is achieved by initializing each neuron that represents a possible combination and then allowing the network settle down into a stable state. The network uses the initialized inputs and the compatibility measures among components in order to divide working area.

• 대한전자공학회논문지SD
• /
• 제45권6호
• /
• pp.16-21
• /
• 2008

본 논문은 새롭게 제안된 단일전자 소자(single-electron device) 및 회로를 이용한 새로운 형태의 홉필드 신경회로망(Hopfield neural network)을 소개한다. 홉필드 신경회로망의 전기적 모델 내부에서 가변저항으로 사용되는 단일전자 시냅스(single-electron synapse)와 비선형 활성함수(nonlinear activation function)로 사용되는 두 단의 단일전자 인버터(single-electron inverter)를 몬테-칼로(Monte-Carlo) 방식의 단일전자 회로 시뮬레이터로 동작을 검증한다.

• 대한전기학회논문지
• /
• 제40권2호
• /
• pp.234-237
• /
• 1991

A new neural network model, based on the Hopfield crossbar associative network, is presented and shown to be an effective tool for the NP-Complete problems. This model is applied to a class of layer assignment problems for VLSI routing. The results indicate that this modified Hopfield model, improves stability and accuracy.

• 전자공학회논문지B
• /
• 제32B권3호
• /
• pp.48-56
• /
• 1995

This paper presents a method of implementing efficient optical flow estimation for dynamic scene analysis using the hierarchical Hopfield neural networks. Given the two consequent inages, Zhou and Chellappa suggested the Hopfield neural network for computing the optical flow. The major problem of this algorithm is that Zhou and Chellappa's network accompanies self-feedback term, which forces them to check the energy change every iteration and only to accept the case where the lower the energy level is guaranteed. This is not only undesirable but also inefficient in implementing the Hopfield network. The another problem is that this model cannot allow the exact computation of optical flow in the case that the disparities of the moving objects are large. This paper improves the Zhou and Chellapa's problems by modifying the structure of the network to satisfy the convergence condition of the Hopfield model and suggesting the hierarchical algorithm, which enables the computation of the optical flow using the hierarchical structure even in the presence of large disparities.

• 제어로봇시스템학회논문지
• /
• 제8권2호
• /
• pp.120-125
• /
• 2002

An optimization approach is used to partition the field of view. A cost function is defined to represent the constraints on the solution, which is then mapped onto a two-dimensional Hopfield neural network for minimization. Each neuron in the network represents a possible match between a field of view and one or multiple objects. Partition is achieved by initializing each neuron that represents a possible match and then allowing the network to settle down into a stable state. The network uses the initial inputs and the compatibility measures between a field of view and one or multiple objects to find a stable state.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.257-260
• /
• 1996

This study is about the construction of algorithm for selecting Yongshin of the Four Pillars. To emulate the method the expert uses when he select the Yongshin, we introduce the Hopfield Network. The result of the simulation classified with Yongshin is presented.

• 한국지능시스템학회논문지
• /
• 제10권3호
• /
• pp.211-217
• /
• 2000

A main contribution of this paper is the development of a Hopfield network-based algorithm for the fault diagnosis of the actuators in linear system with uncertainties. An unknown input decoupling approach is introduced to the design of an adaptive observer so that the observer is insensitive to uncertainties. As a result, the output observation error equation does not depend on the effect of uncertainties. Simultaneous energy minimization by the Hopfield network is used to minimize the least mean square of errors of errors of estimates of output variables. The Hopfield network provides an estimate of the gains of the actuators. When the system dynamics changes, identified gains go through a transient period and this period is used to detect faults. The proposed scheme is demonstrated through its application to a simulated second-order system.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.147-151
• /
• 1991

In this paper a time-optimal path planning scheme for the multiple robot manipulators will be proposed by using hopfield neural network. The time-optimal path planning, which can allow multiple robot system to perform the demanded tasks with a minimum execution time and collision avoidance, may be of consequence to improve the productivity. But most of the methods proposed till now suffers from a significant computational burden and thus limits the on-line application. One way to avoid such a difficulty is to rearrange the problem as MTSP(Multiple Travelling Salesmen Problem) and then apply the Hopfield network technique, which can allow the parallel computation, to the minimum time problem. This paper proposes an approach for solving the time-optimal path planning of the multiple robots by using Hopfield neural network. The effectiveness of the proposed method is demonstrated by computer simulation.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집A
• /
• pp.667-672
• /
• 2001

An optimization approach is used to partition the field of view. A cost function is defined to represent the constraints on the solution, which is then mapped onto a two-dimensional Hopfield neural network for minimization. Each neuron in the network represents a possible match between a field of view and one or multiple objects. Partition is achieved by initializing each neuron that represents a possible match and then allowing the network to settle down into a stable state. The network uses the initial inputs and the compatibility measures between a field of view and one or multiple objects to find a stable state.