• 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.

• 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.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• Journal of the Korea Convergence Society
• /
• v.9 no.6
• /
• pp.39-44
• /
• 2018

The application of deep neural networks to finance has received a great deal of attention from researchers because no assumption about a suitable mathematical model has to be made prior to forecasting and they are capable of extracting useful information from large sets of data, which is required to describe nonlinear input-output relations of financial time series. The paper presents a new deep neural network model where single layered autoencoder and 4 layered neural network are serially coupled for stock price forecasting. The autoencoder extracts deep features, which are fed into multi-layer neural networks to predict the next day's stock closing prices. The proposed deep neural network is progressively learned layer by layer ahead of the final learning of the total network. The proposed model to predict daily close prices of KOrea composite Stock Price Index (KOSPI) is built, and its performance is demonstrated.

• Journal of Educational Research in Mathematics
• /
• v.19 no.3
• /
• pp.425-441
• /
• 2009

The cube-accumulation is a new theme included in the 7th elementary mathematics curriculum for improving children's spatial ability. One activity of the cube-accumulation is to recognize the configuration of accumulated cube given three plane figures in the directions of the above, the front and the side, respectively. The approach to this activity presented in the mathematics textbook is more or less intuitive and constructive, and difficult to some children. So we suggest an alternative, more analytic method, 'elimination method', that is eliminating unnecessary parts from $n{\times}n{\times}n$ whole cubes. This method was adopted to the 32 sixth graders, in special five applicants among them. Their responses and activities were analyzed. We confirm that we can teach the cube-accumulation by the elimination method, and some children prefer this method. 13u1 this method requires more exercises to be executed skillfully.

• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.693-702
• /
• 2019

Deep learning has gained popularity for the classification and prediction task. Neural network layers become deeper as more data becomes available. Saturation is the phenomenon that the gradient of an activation function gets closer to 0 and can happen when the value of weight is too big. Increased importance has been placed on the issue of saturation which limits the ability of weight to learn. To resolve this problem, Glorot and Bengio (Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 249-256, 2010) claimed that efficient neural network training is possible when data flows variously between layers. They argued that variance over the output of each layer and variance over input of each layer are equal. They proposed a method of initialization that the variance of the output of each layer and the variance of the input should be the same. In this paper, we propose a new method of establishing initialization by adopting truncated normal distribution and truncated cauchy distribution. We decide where to truncate the distribution while adapting the initialization method by Glorot and Bengio (2010). Variances are made over output and input equal that are then accomplished by setting variances equal to the variance of truncated distribution. It manipulates the distribution so that the initial values of weights would not grow so large and with values that simultaneously get close to zero. To compare the performance of our proposed method with existing methods, we conducted experiments on MNIST and CIFAR-10 data using DNN and CNN. Our proposed method outperformed existing methods in terms of accuracy.