• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.13-15
• /
• 2006

When we use multilayer perceptron model for pattern classification probmems, we allocate one output node for each class. In this paper, we increase the number of output nodes for each class and investigate the performance of multilayer perceptrons through the simulation of isolated-word recognition problems.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.11a
• /
• pp.213-217
• /
• 2003

In this paper, we analysize the noise robustness of MLPs(Multilayer perceptrons). Also, as a preprocessing stage of MLPs to improve noise robustness, we consider the ICA(independent component analysis) and PCA(principle component analysis). After analyzing the noise redunction effect using PCA or ICA, we verify the noise robustness of MLPs through handwritten-digit recognition simulations.

• The Journal of the Korea Contents Association
• /
• v.9 no.1
• /
• pp.123-130
• /
• 2009

When we apply MLPs(multilayer perceptrons) to pattern classification problems, we generally allocate one output node for each class and the index of output node denotes a class. On the contrary, in this paper, we propose to increase the number of output nodes per each class for performance improvement of MLPs. For theoretical backgrounds, we derive the misclassification probability in two class problems with additional outputs under the assumption that the two classes have equal probability and outputs are uniformly distributed in each class. Also, simulations of 50 isolated-word recognition show the effectiveness of our method.

• The Journal of the Korea Contents Association
• /
• v.4 no.3
• /
• pp.99-105
• /
• 2004

This paper proposes optimal learning rates in the gradient descent training of multilayer perceptrons, which are a separate learning rate for weights associated with each neuron and a separate one for assigning virtual hidden targets associated with each training pattern 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.9 no.1
• /
• pp.159-166
• /
• 2009

In this paper, we analyse the noise robustness of MLPs(Multilayer perceptrons) through deriving the probability density function(p.d.f.) of output nodes with additive input noises and the misclassification ratio with the integral form of the p.d.f. functions. Also, we propose linear preprocessing methods to improve the noise robustness. As a preprocessing stage of MLPs, we consider ICA(independent component analysis) and PCA(principle component analysis). After analyzing the noise reduction effect using PCA or ICA in the viewpoints of SNR(Singal-to-Noise Ratio), we verify the preprocessing effects through the simulations of handwritten-digit recognition problems.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.700-702
• /
• 2004

A local-step optimization method is proposed to supplement the global-step optimization methods which adopt online update mode of internal weights and error energy as stop criterion in learning of multilayer perceptrons (MLPs). This optimization method is applied to the standard online error backpropagation(EBP) and the performance is evaluated for a speaker verification system.

• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.141-148
• /
• 2009

Recently there have been many research efforts focused on imbalanced data classification problems, since they are pervasive but hard to be solved. Approaches to the imbalanced data problems can be categorized into data level approach using re-sampling, algorithmic level one using cost functions, and ensembles of basic classifiers for performance improvement. As an algorithmic level approach, this paper proposes to use multilayer perceptrons with higher-order error functions. The error functions intensify the training of minority class patterns and weaken the training of majority class patterns. Mammography and thyroid data-sets are used to verify the superiority of the proposed method over the other methods such as mean-squared error, two-phase, and threshold moving methods.

• 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.

• The Journal of the Korea Contents Association
• /
• v.10 no.5
• /
• pp.99-106
• /
• 2010

Multilayer perceptrons(MLPs) or feed-forward neural networks are widely applied to many areas based on their function approximation capabilities. When implementing MLPs for application problems, we should determine various parameters and training methods. In this paper, we discuss the design of MLPs especially for pattern classification problems. This discussion includes how to decide the number of nodes in each layer, how to initialize the weights of MLPs, how to train MLPs among various error functions, the imbalanced data problems, and deep architecture.

• Communications for Statistical Applications and Methods
• /
• v.14 no.3
• /
• pp.601-608
• /
• 2007

Lee, et al. (1999) proposed a unique but universal robust objective function replacing the square objective function for the radial basis function network, and demonstrated some advantages. In this article, the robust objective function in Lee, et al. (1999) is adapted for a multilayer perceptron (MLP). The shape of the robust objective function is formed by the scale parameter. Another method of determining a proper value of that parameter is proposed.