• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.853-858
• /
• 1993

The error back-propagation(BP) algorithm is widely used for finding optimum weights of multi-layer neural networks. However, the critical drawback of the BP algorithm is its slow convergence of error. The major reason for this slow convergence is the premature saturation which is a phenomenon that the error of a neural network stays almost constant for some period time during learning. An inappropriate selections of initial weights cause each neuron to be trapped in the premature saturation state, which brings in slow convergence speed of the multi-layer neural network. In this paper, to overcome the above problem, Micro-Genetic algorithms(.mu.-GAs) which can allow to find the near-optimal values, are used to select the proper weights and slopes of activation function of neurons. The effectiveness of the proposed algorithms will be demonstrated by some computer simulations of two d.o.f planar robot manipulator.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.686-692
• /
• 2022

In this paper, the matching error rates of modified area-based, energy-based algorithms, and learning-based structures were compared for stereo image matching. Census transform (CT) based on region and life propagation (BP) algorithm based on energy were selected, respectively.Existing algorithms have been improved and implemented in an embedded processor environment so that they can be used for stereo image matching in mobile systems. Even in the case of the learning base to be compared, a neural network structure that utilizes small-scale parameters was adopted. To compare the error rates of the three matching methods, Middlebury's Tsukuba was selected as a test image and subdivided into non-occlusion, discontinuous, and disparity error rates for accurate comparison. As a result of the experiment, the error rate of modified CT matching improved by about 11% when compared with the existing algorithm. BP matching was about 87% better than conventional CT in the error rate. Compared to the learning base using neural networks, BP matching was about 31% superior.

• Proceedings of the KAIS Fall Conference
• /
• 2006.11a
• /
• pp.186-190
• /
• 2006

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1574-1575
• /
• 2007

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.260-264
• /
• 1998

In this paper, we implemented the neuro-computer called MY-NEUPOWER in our research to carry out the artificial neural networks (ANN) calculating. An application software was developed based on a neural network using back-propagation (BP) algorithm under the UNIX platform by the specified computer language named MYPARAL. This neural network model was used as an auxiliary controller in the temperature control of sinter cooler system in steel plant which is a nonlinear system. The neural controller was trained off-line using the real input-output data as training pairs. We also made the system description of adaptive neural controller on the same temperature control system. We will carry out the whole system simulation to verify the suitability of neural controller in improving the system features.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.4
• /
• pp.350-357
• /
• 1991

A speech recognition system based on a neural network, which can be used for telephon number services was tested. Because in Korea two different cardinal number systems, a koreanic one and a sinokoreanic one, are in use, it is necessary that the used systems is able to recognize 22 discret words. The structure of the neural network used had two layers, also a structure with 3 layers, one hidden layreformed of each 11, 22 and 44 hidden units was tested. During the learning phase of the system the so called BP-algorithm (back propagation) was applied. The process of learning can e influenced by using a different learning factor and also by the method of learning(for instance random or cycle). The optimal rate of speaker independent recognition by using a 2 layer neural network was 96%. A drop of recognition was observed by overtraining. This phenomen appeared more clearly if a 3 layer neural network was used. These phenomens are described in this paper in more detail. Especially the influence of the construction of the neural network and the several states during the learning phase are examined.

• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1338-1347
• /
• 2013

Face recognition is a science of automatically identifying individuals based their unique facial features. In order to avoid overfitting and reduce the computational reduce the computational burden, a new face recognition algorithm using PCA-fisher linear discriminant (PCA-FLD) and fuzzy radial basis function neural network (RBFNN) is proposed in this paper. First, face features are extracted by the principal component analysis (PCA) method. Then, the extracted features are further processed by the Fisher's linear discriminant technique to acquire lower-dimensional discriminant patterns, the processed features will be considered as the input of the fuzzy RBFNN. As a widely applied algorithm in fuzzy RBF neural network, BP learning algorithm has the low rate of convergence, therefore, an improved learning algorithm based on Levenberg-Marquart (L-M) for fuzzy RBF neural network is introduced in this paper, which combined the Gradient Descent algorithm with the Gauss-Newton algorithm. Experimental results on the ORL face database demonstrate that the proposed algorithm has satisfactory performance and high recognition rate.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.151-155
• /
• 1996

To automate an excavator the control issues resulting from environmental uncertainties must be solved. In particular the interactions between the excavation tool and the excavation environment are dynamic, unstructured and complex. In addition, operating modes of an excavator depend on working conditions, which makes it difficult to derive the exact mathematical model of excavator. Even after the exact mathematical model is established, it is difficult to design of a controller because the system equations are highly nonlinear and the state variable are coupled. The objective of this study is to design a multi-layer neural network which controls the position of excavator's attachment. In this paper, a dynamic controller has been developed based on an error back-propagation(BP) neural network. Computer simulation results demonstrate such powerful characteristics of the proposed controller as adaptation to changing environment, robustness to disturbance and performance improvement with the on-line learning in the position control of excavator attachment.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.3
• /
• pp.215-220
• /
• 2002

This paper proposes a method to apply the Backpropagation(BP) algorithm of MVL(Multi-Valued Logic) Neural Network to pattern recognition. It extracts the property of an object density about an original pattern necessary for pattern processing and makes the property of the object density mapped to MVL. In addition, because it team the pattern by using multiple valued logic, it can reduce time f3r pattern and space fer memory to a minimum. There is, however, a demerit that existed MVL cannot adapt the change of circumstance. Through changing input into MVL function, not direct input of an existed Multiple pattern, and making it each variable loam by neural network after calculating each variable into liter function. Error has been reduced and convergence speed has become fast.

• Journal of Digital Contents Society
• /
• v.8 no.3
• /
• pp.393-401
• /
• 2007

P2P systems have gained a lot of research interests and popularity over the years and have the capability to unleash and distribute awesome amounts of computing power, storage and bandwidths currently languishing - often underutilized - within corporate enterprises and every Internet connected home in the world. Since there is no central control over resources or devices and no before hand information about the resources or devices, device discovery remains a substantial problem in P2P environment. In this paper, we cover some of the current solutions to this problem and then propose our feed forward neural network (FFNN) based solution for device discovery in mobile P2P environment. We implements feed forward neural network (FFNN) trained with back propagation (BP) algorithm for device discovery and show, how large computation task can be distributed among such devices using agent technology. It also shows the possibility to use our architecture in home networking where devices have less storage capacity.