• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.215-222
• /
• 2001

Neural network based models of semiconductor manufacturing processes have been shown to offer advantages in both accuracy and generalization over traditional methods. However, model development is often complicated by the fact that back-propagation neural networks contain several adjustable parameters whose optimal values unknown during training. These include learning rate, momentum, training tolerance, and the number of hidden layer neurOnS. This paper presents an investigation of the use of genetic algorithms (GAs) to determine the optimal neural network parameters for the modeling of plasma-enhanced chemical vapor deposition (PECVD) of silicon dioxide films. To find an optimal parameter set for the neural network PECVD models, a performance index was defined and used in the GA objective function. This index was designed to account for network prediction error as well as training error, with a higher emphasis on reducing prediction error. The results of the genetic search were compared with the results of a similar search using the simplex algorithm.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1285-1288
• /
• 1998

In this paper, we propose a new learning algorithm for multilayer neural networks. In the error backpropagation that is widely used for training multilayer neural networks, weights are adjusted to reduce the error function that is sum of squared error for all the neurons in the output layer of the network. In the proposed learning algorithm, we consider each output of the output layer as a function of weights and adjust the weights directly so that the output neurons produce the desired outputs. Experiments show that the proposed algorithm outperforms the backpropagation learning algorithm.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.4
• /
• pp.243-248
• /
• 2013

In this thesis, we have designed the indirect adaptive controller using Dynamic Neural Units(DNU) for unknown nonlinear systems. Proposed indirect adaptive controller using Dynamic Neural Unit 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 method is 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 training.

• Proceedings of the KAIS Fall Conference
• /
• 2007.11a
• /
• pp.81-84
• /
• 2007

In this thesis, we have designed the indirect adaptive controller using Dynamic Neural Units(DNU) for unknown nonlinear systems. Proposed indirect adaptive controller using Dynamic Neural Unit 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 method is 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 training.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.1019-1029
• /
• 2020

In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.3-5
• /
• 2007

This paper presents decision feedback equalizers using a recurrent neural network trained algorithm using extended Kalman filter(EKF) and sigma-point Kalman filter(SPKF). EKF is propagated, analytically through the first-order linearization of the nonlinear system. This can introduce large errors in the true posterior mean and covariance of the Gaussian random variable. The SPKF addresses this problem by using a deterministic sampling approach. The features of the proposed recurrent neural equalizer And we investigate the bit error rate(BER) between EKF and SPKF.

• Proceedings of the KIPE Conference
• /
• 1999.07a
• /
• pp.526-530
• /
• 1999

This paper presents a newly developed speed sensorless drive using Neural Network algorithm. Neural Network algorithm can be divided into three categories. In the first one, a Back Propagation-based NN algorithm is well-known to gradient descent method. In the second scheme, a Extended Kalman Filter-based NN algorithm has just the time varying learning rate. In the last scheme, a Recursive Least Square-based NN algorithm is faster and more stable than the classical back-propagation algorithm for training multilayer perceptrons. The number of iterations required to converge and the mean-squared error between the desired and actual outputs is compared with respect to each method. The theoretical analysis and experimental results are discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3749-3768
• /
• 2018

As one of the most potential types of low-density parity-check (LDPC) codes, CPM-QC-LDPC code has considerable advantages but there still exist some limitations in practical application, for example, the existing decoding algorithm has a low convergence rate and a high decoding complexity. According to the structural property of this code, we propose a new method based on a CPM-RID decoding algorithm that decodes block-by-block with weights, which are obtained by neural network training. From the simulation results, we can conclude that our proposed method not only improves the bit error rate and frame error rate performance but also increases the convergence rate, when compared with the original CPM-RID decoding algorithm and scaled MSA algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.214-217
• /
• 1999

In this paper, genetic algorithm (GA) is implemented to search for the optimal structures (i.e. the kind of neural networks, the number of inputs and hidden neurons) of neural networks which are used approximating a given nonlinear function. Two kinds of neural networks, i.e. the multilayer feedforward [1] and time delay neural networks (TDNN) [2] are involved in this paper. The synapse weights of each neural network in each generation are obtained by associated training algorithms. The simulation results of nonlinear function approximation are given out and some improvements in the future are outlined.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.473-481
• /
• 2008

This paper presents an approach to Back-propagation and Radial Basis Function neural network method with various training set for automatic vehicle detection from aerial images. The initial extraction of candidate object is based on Mean-shift algorithm with symmetric property of a vehicle structure. By fusing the density and the symmetry, the method can remove the ambiguous objects and reduce the cost of processing in the next stage. To extract features from the detected object, we describe the object as a log-polar shape histogram using edge strengths of object and represent the orientation and distance from its center. The spatial histogram is used for calculating the momentum of object and compensating the direction of object. BPNN and RBFNN are applied to verify the object as a vehicle using a variety of non-car training sets. The proposed algorithm shows the results which are according to the training data. By comparing the training sets, advantages and disadvantages of them have been discussed.