• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.364-370
• /
• 2005

LBL(Layer-By-Layer) algorithms have been proposed to accelerate the training speed of MLPs(Multilayer Perceptrons). In this LBL algorithms, each layer needs a error function for optimization. Especially, error function for hidden layer has a great effect to achieve good performance. In this sense, this paper proposes a new hidden layer error function for improving the performance of LBL algorithm for MLPs. The hidden layer error function is derived from the mean squared error of output layer. Effectiveness of the proposed error function was demonstrated for a handwritten digit recognition and an isolated-word recognition tasks and very fast learning convergence was obtained.

• The Journal of the Korea Contents Association
• /
• v.5 no.6
• /
• pp.57-64
• /
• 2005

LBL(Layer-By-Layer) algorithms have been proposed to accelerate the training speed of MLPs(Multilayer Perceptrons). In this LBL algorithms, each layer needs a error function for optimization. Especially, error function for hidden layer has a great effect to achieve good performance. In this sense, this paper proposes a new hidden layer error function for improving the performance of LBL algorithm for MLPs. The hidden layer error function is derived from the mean squared error of output layer. Effectiveness of the proposed error function was demonstrated for a handwritten digit recognition and an isolated-word recognition tasks and very fast learning convergence was obtained.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.7
• /
• pp.814-820
• /
• 2011

It takes long time in numerical simulation because structural design for tire requires the nonlinear material property. Neural networks has been widely studied to engineering design to reduce numerical computation time. The numbers of hidden layer, hidden layer neuron and training data have been considered as the structural design variables of neural networks. In application of neural networks to optimize design, there are a few studies about arrangement method of input layer neurons. To investigate the effect of input layer neuron arrangement on neural networks, the variables of tire contour design and tension in bead area were assigned to inputs and output for neural networks respectively. Design variables arrangement in input layer were determined by main effect analysis. The number of hidden layer, the number of hidden layer neuron and the number of training data and so on have been considered as the structural design variables of neural networks. In application to optimization design problem of neural networks, there are few studies about arrangement method of input layer neurons. To investigate the effect of arrangement of input neurons on neural network learning tire contour design parameters and tension in bead area were assigned to neural input and output respectively. Design variables arrangement in input layer was determined by main effect analysis.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1075-1086
• /
• 2018

In this paper a cross-validation algorithm for training probabilistic neural networks (PNNs) is presented in order to be applied to automatic face identification. Actually, standard PNNs perform pretty well for small and medium sized databases but they suffer from serious problems when it comes to using them with large databases like those encountered in biometrics applications. To address this issue, we proposed in this work a new training algorithm for PNNs to reduce the hidden layer's size and avoid over-fitting at the same time. The proposed training algorithm generates networks with a smaller hidden layer which contains only representative examples in the training data set. Moreover, adding new classes or samples after training does not require retraining, which is one of the main characteristics of this solution. Results presented in this work show a great improvement both in the processing speed and generalization of the proposed classifier. This improvement is mainly caused by reducing significantly the size of the hidden layer.

• Structural Engineering and Mechanics
• /
• v.77 no.1
• /
• pp.47-56
• /
• 2021

This paper deals with damage detection using a Gapped Smoothing Method (GSM) combined with deep learning. Convolutional Neural Network (CNN) is a model of deep learning. CNN has an input layer, an output layer, and a number of hidden layers that consist of convolutional layers. The input layer is a tensor with shape (number of images) × (image width) × (image height) × (image depth). An activation function is applied each time to this tensor passing through a hidden layer and the last layer is the fully connected layer. After the fully connected layer, the output layer, which is the final layer, is predicted by CNN. In this paper, a complete machine learning system is introduced. The training data was taken from a Finite Element (FE) model. The input images are the contour plots of curvature gapped smooth damage index. A free-free beam is used as a case study. In the first step, the FE model of the beam was used to generate data. The collected data were then divided into two parts, i.e. 70% for training and 30% for validation. In the second step, the proposed CNN was trained using training data and then validated using available data. Furthermore, a vibration experiment on steel damaged beam in free-free support condition was carried out in the laboratory to test the method. A total number of 15 accelerometers were set up to measure the mode shapes and calculate the curvature gapped smooth of the damaged beam. Two scenarios were introduced with different severities of the damage. The results showed that the trained CNN was successful in detecting the location as well as the severity of the damage in the experimental damaged beam.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.8
• /
• pp.1239-1249
• /
• 1990

In this paper, using the neural network design techniques, an adaptive Mahalanobis distance classifier(AMDC) is designed. This classifier has three layers: input layer, internal layer and output layer. The connection from input layer to internal layer is fully connected, and that from internal to output layer has partial connection that might be thought as an Oring. If two ormore clusters of patterns of one class are laid apart in the feature space, the network adaptively generate the internal nodes, whhch are corresponding to the subclusters of that class. The number of the output nodes in just same as the number of the classes to classify, on the other hand, the number of the internal nodes is defined by the number of the subclusters, and can be optimized by itself. Using the method of making the subclasses, the different patterns that are of the same class can easily be distinguished from other classes. If additional training is needed after the completion of the traning, the AMDC does not have to repeat the trainging that has already done. To test the performance of the AMDC, the experiments of classifying 500 Hangeuls were done. In experiment, 20 print font sets of Hangeul characters(10,000 cahracters) were used for training, and with 3 sets(1,500 characters), the AMDC was tested for various initial variance \ulcornerand threshold \ulcorner and compared with other statistical or neural classifiers.

• Journal of Korean Ophthalmic Optics Society
• /
• v.19 no.2
• /
• pp.247-252
• /
• 2014

Purpose: This study was to investigate the properties and the location of neural reorganization following eccentric viewing training. Methods: 14 subjects with normal vision took part in eccentric viewing training. The measurements of the light sensitivity and multifocal electroretinogram were performed before and after the training. Results: The measurements of the light sensitivity and multifocal electroretinogram for pre-eccentric viewing training and post-eccentric viewing training showed the significant difference (p<0.047 and p<0.028, respectively). Conclusions: The retinal outer plexiform layer is unable to regenerate. However, the neural reorganization in the retinal outer plexiform layer is able to take place following eccentric viewing training.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.381-388
• /
• 2023

Through artificial neural network education using spreadsheets, non-major undergraduate students can understand the operation principle of artificial neural networks and develop their own artificial neural network software. Here, training of the operation principle of artificial neural networks starts with the generation of training data and the assignment of correct answer labels. Then, the output value calculated from the firing and activation function of the artificial neuron, the parameters of the input layer, hidden layer, and output layer is learned. Finally, learning the process of calculating the error between the correct label of each initially defined training data and the output value calculated by the artificial neural network, and learning the process of calculating the parameters of the input layer, hidden layer, and output layer that minimize the total sum of squared errors. Training on the operation principles of artificial neural networks using a spreadsheet was conducted for undergraduate non-major students. And image training data and basic artificial neural network development results were collected. In this paper, we analyzed the results of collecting two types of training data and the corresponding artificial neural network SW with small 12-pixel images, and presented methods and execution results of using the collected training data for Orange machine learning model learning and analysis tools.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.12
• /
• pp.27-37
• /
• 1991

In this paper, the novel PLD (Preceding Layer Driven) MLP (Multi Layer Perceptron) neural network model and its learning algorithm is described. This learning algorithm is different from the conventional. This integer weights and hard limit function are used for synaptic weight values and activation function, respectively. The entire learning process is performed by layer-by-layer method. the number of layers can be varied with difficulty of training data. Since the synaptic weight values are integers, the synapse circuit can be easily implemented with CMOS. PLD MLP neural network was applied to English Characters, arbitrary waveform generation and spiral problem.

• Journal of Environmental Science International
• /
• v.11 no.3
• /
• pp.201-207
• /
• 2002

This study was carried out to evaluate the artificial neural network algorithm for water quality forecasting in Chungju lake, north Chungcheong province. Multi-layer perceptron(MLP) was used to train artificial neural networks. MLP was composed of one input layer, two hidden layers and one output layer. Transfer functions of the hidden layer were sigmoid and linear function. The number of node in the hidden layer was decided by trial and error method. It showed that appropriate node number in the hidden layer is 10 for pH training, 15 for DO and BOD, respectively. Reliability index was used to verify for the forecasting power. Considering some outlying data, artificial neural network fitted well between actual water quality data and computed data by artificial neural networks.