• Proceedings of the KIEE Conference
• /
• 1990.07a
• /
• pp.539-541
• /
• 1990

A new neural network model, based on the Hopfield's 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.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.5
• /
• pp.561-570
• /
• 1989

In this paper, we describe the theoretical analysis and optical implementation of real-time associative memory based on the modified Hopfield neural network model by using a commerical LCTV connected to computer graphic as the real-time memory mask and adding one mask line to the momory mask in order to optically obtain the time-varing thresholding values of the modified Hopfield model.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.2
• /
• 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.

• Structural Engineering and Mechanics
• /
• v.7 no.5
• /
• pp.485-502
• /
• 1999

Using the continuous Hopfield network model as the basis to solve the general crisp and fuzzy constrained optimization problem is presented and examined. The model lies in its transformation to a parallel algorithm which distributes the work of numerical optimization to several simultaneously computing processors. The method is applied to different structural engineering design problems that demonstrate this usefulness, satisfaction or potential. The computing algorithm has been given and discussed for a designer who can program it without difficulty.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1774-1777
• /
• 1997

As factory automation is required, using the vision system is also essential. Especially, the pateh planning of parts with J-lead on PCB plays a import role of whole automation. Path planning is required because J-lead is scatteed compaed to L-lead on PCB. Therefore, in this paper, we propose path planning of part inspection with J-lead to use Hopfield Model(TSP : Traveling Salesman Problem). Then optical system suited to J-lead inspection is designed and the algorithm of J-lead solder joint and part inspection is proposed.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• 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.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.10
• /
• pp.1591-1597
• /
• 1989

Through the matematical alaysis of EX-NOR logic relation between the input vector and the memory matrix, we propose a new method for optical implementation of the bipolar Hopfield neural network model based on the optical vector-matrix multiplier.

• Journal of Astronomy and Space Sciences
• /
• v.26 no.2
• /
• pp.211-220
• /
• 2009

As one of the GNSS error simulation case studies, we computed tropospheric signal delays based on three well-known models (Hopfield, Modified Hopfield and Saastamoinen) and a simple model. In the computation, default meteorological values were used. The result was compared with the GIPSY result, which we assumed as truth. The RMS of a simple model with Marini mapping function was the largest, 31.0 cm. For the other models, the average RMS is 5.2 cm. In addition, to quantify the influence of the accuracy of meteorological information on the signal delay, we did sensitivity analysis of pressure and temperature. As a result, all models used this study were not very sensitive to pressure variations. Also all models, except for the modified Hopfield model, were not sensitive to temperature variations.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.6
• /
• pp.16-21
• /
• 2008

This paper introduces a new type of Hopfield neural network using newly developed single-electron devices. In the electrical model of the Hopfield neural network, a single-electron synapse, used as a voltage(or current)-variable resistor, and two stages of single-electron inverters, used as a nonlinear activation function, are simulated with a single-electron circuit simulator using Monte-Carlo method to verily their operation.