• The Journal of Information Technology and Database
• /
• v.2 no.2
• /
• pp.71-85
• /
• 1995

Many research results conducted by neural network researchers have claimed that the classification accuracy of neural networks is superior to, or at least equal to that of conventional methods. However, in series of neural network classifications, it was found that the classification accuracy strongly depends on the characteristics of training data set. Even though there are many research reports that the classification accuracy of neural networks can be different, depending on the composition and architecture of the networks, training algorithm, and test data set, very few research addressed the problem of classification accuracy when the basic assumption of data monotonicity is violated, In this research, development project of automated credit evaluation system is described. The finding was that arrangement of training data is critical to successful implementation of neural training to maintain monotonicity of the data set, for enhancing classification accuracy of neural networks.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.4
• /
• pp.338-344
• /
• 2002

In this paper, neural network force tracking control is proposed. The conventional impedance function is reformulated to have direct farce tracking capability. Neural network is used to compensate for all the uncertainties such as unknown robot dynamics, unknown environment stiffness, and unknown environment position. On line training signal of farce error for neural network is formulated. A large x-y table is built as a test-bed and neural network loaming algorithm is implemented on a DSP board mounted in a PC. Experimental studies of farce tracking on unknown environment for x-y table robot are presented to confirm the performance of the proposed technique.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.201-207
• /
• 2012

A RAM-based neural network is a weightless neural network based on binary neural network(BNN) which is efficient neural network with a one-shot learning. RAM-based neural network has multiful information bits and store counts of training in BNN. Supervised learning based on the RAM-based neural network has the excellent performance in pattern recognition but in pattern categorization with unsupervised learning as unsuitable. In this paper, we propose a unsupervised learning algorithm in the RAM-based neural network to perform pattern categorization. By the proposed unsupervised learning algorithm, RAM-based neural network create categories depending on the input pattern by itself. Therefore, RAM-based neural network for supervised learning and unsupervised learning should proof of all possible complex models. The training data for experiments provided by the MNIST offline handwritten digits which is consist of 0 to 9 multi-pattern.

• Journal of Digital Contents Society
• /
• v.18 no.5
• /
• pp.969-976
• /
• 2017

This paper proposes the learning method of an artificial neural network and a convolutional neural network using the WFSO algorithm developed as an optimization algorithm. Since the optimization algorithm searches based on a number of candidate solutions, it has a drawback in that it is generally slow, but it rarely falls into the local optimal solution and it is easy to parallelize. In addition, the artificial neural networks with non-differentiable activation functions can be trained and the structure and weights can be optimized at the same time. In this paper, we describe how to apply WFSO algorithm to artificial neural network learning and compare its performances with error back-propagation algorithm in multilayer artificial neural networks and convolutional neural networks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.216-221
• /
• 2004

This paper describes an optimal synthesis method of binary neural network for pattern recognition. Our objective is to minimize the number of connections and the number of neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm (NETLA) for the multilayered neural networks. The synthesis method in NETLA uses the Expanded Sum of Product (ESP) of the boolean expressions and is based on the multilayer perceptron. It has an ability to optimize a given binary neural network in the binary space without any iterative learning as the conventional Error Back Propagation (EBP) algorithm. Furthermore, NETLA can reduce the number of the required neurons in hidden layer and the number of connections. Therefore, this learning algorithm can speed up training for the pattern recognition problems. The superiority of NETLA to other learning algorithms is demonstrated by an practical application to the approximation problem of a circular region.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.171-174
• /
• 2003

In this paper, a Learning module for a reconfigurable neural network processor(ERNIE) was proposed for an On-chip learning. The existing reconfigurable neural network processor(ERNIE) has a much better performance than the software program but it doesn't support On-chip learning function. A learning module which is based on Back Propagation algorithm was designed for a help of this weak point. A pipeline structure let the learning module be able to update the weights rapidly and continuously. It was tested with five types of alphabet font to evaluate learning module. It compared with C programed neural network model on PC in calculation speed and correctness of recognition. As a result of this experiment, it can be found that the neural network processor(ERNIE) with learning module decrease the neural network training time efficiently at the same recognition rate compared with software computing based neural network model. This On-chip learning module showed that the reconfigurable neural network processor(ERNIE) could be a evolvable neural network processor which can fine the optimal configuration of network by itself.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.52-58
• /
• 2005

We have developed a Group Method of Data Handling (GMDH) type algorithm for designing multi-layered neural networks. The algorithm is general enough that it will accept any number of inputs and any sized training set. Each neuron of the resulting network is a function of two of the inputs to the layer. The equation for each of the neurons is a quadratic polynomial. Several forms of the equation are tested for each neuron to make sure that only the best equation of two inputs is kept. All possible combinations of two inputs to each layer are also tested. By carefully testing each resulting neuron, we have developed an algorithm to keep only the best neurons at each level. The algorithm's goal is to create as accurate a network as possible while minimizing the size of the network. Software was developed to train and simulate networks using our algorithm. Several applications were modeled using our software, and the result was that our algorithm succeeded in developing small, accurate, multi-layer networks.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.7
• /
• pp.531-535
• /
• 2004

A new method is presented to construct a classifier. This was accomplished by combining a generalized regression neural network (GRNN) and a genetic algorithm (GA). The classifier constructed in this way is referred to as a GA-GRNN. The GA played a role of controlling training factors simultaneously. The GA-GRNN was applied to classify 4 different Promoter sequences. The training and test data were composed of 115 and 58 sequence patterns, respectively. The classifier performance was investigated in terms of the classification sensitivity and prediction accuracy. Compared to conventional GRNN, GA-GRNN significantly improved the total classification sensitivity as well as the total prediction accuracy. As a result, the proposed GA-GRNN demonstrated improved classification sensitivity and prediction accuracy over the convention GRNN.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.275-280
• /
• 2005

The principal context of this research is the approach to an artificial neural network algorithm which solves multivariable nonlinear equation systems by estimating the state of line power flow. First a dynamical neural network with feedback is used to find the minimum value of the objective function at each iteration of the state estimator algorithm. In second step a two-layer neural network structures is derived to implement all of the different matrix-vector products that arise in neural network state estimator analysis. For hardware requirements, as they relate to the total number of internal connections, the architecture developed here preserves in its structure the pronounced sparsity of power networks for which state the estimator analysis is to be carried out. A principal feature of the architecture is that the computing time overheads in solution are independent of the dimensions or structure of the equation system. It is here where the ultrahigh-speed of massively parallel computing in neural networks can offer major practical benefit.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.6 no.1
• /
• pp.27-33
• /
• 1997

A neural network approach has been developed to determine the depth of a surface breaking crack in a steel plate from ultrasonic backscattering data. The network is trained by the use of feedforward three-layered network together with a back-scattering algorithm for error correction. The signal used for crack insonification is a mode converted 70$^{\circ}$transverse wave. A numerical analysis of back scattered field is carried out based on elastic wave theory, by the use of the boundary element method. The numerical data are calibrated by comparison with experimental data. The numerical analysis provides synthetic data for the training of the network. The training data have been calculated for cracks with specified increments of the crack depth. The performance of the network has been tested on other synthetic data and experimental data which are different from the training data.