• Journal of the Korea Society for Simulation
• /
• v.29 no.4
• /
• pp.73-84
• /
• 2020

As the Internet began to become popular, there have been hacking and attacks on networks including systems, and as the techniques evolved day by day, it put risks and burdens on companies and society. In order to alleviate that risk and burden, it is necessary to detect hacking and attacks early and respond appropriately. Prior to that, it is necessary to increase the reliability in detecting network intrusion. This study was conducted on applying weight initialization and weight optimization to the KDD'99 dataset to improve the accuracy of detecting network intrusion. As for the weight initialization, it was found through experiments that the initialization method related to the weight learning structure, like Xavier and He method, affects the accuracy. In addition, the weight optimization was confirmed through the experiment of the network intrusion detection dataset that the Adam algorithm, which combines the advantages of the Momentum reflecting the previous change and RMSProp, which allows the current weight to be reflected in the learning rate, stands out in terms of accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.12
• /
• pp.954-961
• /
• 2013

In this paper, we propose a new learning method using a variable learning to improve pattern recognition in the FCSR(Fast Commit Slow Recode) learning method of the Fuzzy ART. Traditional learning methods have used a fixed learning rate in updating weight vector(representative pattern). In the traditional method, the weight vector will be updated with a fixed learning rate regardless of the degree of similarity of the input pattern and the representative pattern in the category. In this case, the updated weight vector is greatly influenced from the input pattern where it is on the boundary of the category. Thus, in noisy environments, this method has a problem in increasing unnecessary categories and reducing pattern recognition capacity. In the proposed method, the lower similarity between the representative pattern and input pattern is, the lower input pattern contributes for updating weight vector. As a result, this results in suppressing the unnecessary category proliferation and improving pattern recognition capacity of the Fuzzy ART in noisy environments.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.39-47
• /
• 2011

Ergezinger's method, one of the layer-by-layer algorithms used for multilyer perceptrons, consists of an output node and can make premature saturations in the output's weight because of using linear least squared method in the output layer. These saturations are obstacles to learning time and covergence. Therefore, this paper expands Ergezinger's method to be able to use an output vector instead of an output node and introduces a learning rate to improve learning time and convergence. The learning rate is a variable rate that reflects the correlation coefficient between new weight and previous weight while updating hidden's weight. To compare the proposed method with Ergezinger's method, we tested iris recognition and nonlinear approximation. It was found that the proposed method showed better results than Ergezinger's method in learning convergence. In the CPU time considering correlation coefficient computation, the proposed method saved about 35% time than the previous method.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.2
• /
• pp.159-167
• /
• 1996

In this paper, a new competitive learning algorithm called dynamic competitive learning (DCL) is presented. DCL is a supervised learning mehtod that dynamically generates output neuraons and nitializes weight vectors from training patterns. It introduces a new parameter called LOG (limit of garde) to decide whether or not an output neuron is created. In other words, if there exist some neurons in the province of LOG that classify the input vector correctly, then DCL adjusts the weight vector for the neuraon which has the minimum grade. Otherwise, it produces a new output neuron using the given input vector. It is largely learning is not limited only to the winner and the output neurons are dynamically generated int he trining process. In addition, the proposed algorithm has a small number of parameters. Which are easy to be determined and applied to the real problems. Experimental results for patterns recognition of remote sensing data and handwritten numeral data indicate the superiority of dCL in comparison to the conventional competitive learning methods.

• The Journal of Information Technology
• /
• v.8 no.1
• /
• pp.119-124
• /
• 2005

Learning procedure in the neural network is updating of weights between neurons. Unadequate initial learning coefficient causes excessive iterations of learning process or incorrect learning results and degrades learning efficiency. In this paper, adaptive learning algorithm is proposed to increase the efficient in the learning algorithms of Kohonens Self-Organization Neural networks. The algorithm updates the weights adaptively when learning procedure runs. To prove the efficiency the algorithm is experimented to clustering of the random weight. The result shows improved learning rate about 42~55% ; less iteration counts with correct answer.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.142-150
• /
• 1994

This paper deals with fast competitive learning using classified learning rates. The basic idea of the proposed method is to assign a classified learning rate to each weight vector. The weight vector associated with an output node is updated using its own learning rate. Each learning rate is changed only when its corresponding output node wins the competition, and the learning rates of the losing nodes are not changed. The experimental results obtained with image vector quantization show that the proposed method learns more rapidly and yields better quality that conventional competitive learning.

• Journal of the Korea Society for Simulation
• /
• v.19 no.2
• /
• pp.91-98
• /
• 2010

Conventional path-finding has focused on finding short collision-free paths. However, as computer games become more sophisticated, it is required to take tactical information like ambush points or lines of enemy sight into account. One way to make this information have an effect on path-finding is to represent a heuristic function of a search algorithm as a weighted sum of tactics. In this paper we consider the problem of learning heuristic to optimize path-finding based on given tactical information. What is meant by learning is to produce a good weight vector for a heuristic function. Training examples for learning are given by a game level-designer and will be compared with search results in every search level to update weights. This paper proposes a learning algorithm integrated with search for tactical path-finding. The perceptron-like method for updating weights is described and a simulation tool for implementing these is presented. A level-designer can mark desired paths according to characters' properties in the heuristic learning tool and then it uses them as training examples to learn weights and shows traces of paths changing along with weight learning.

• Structural Engineering and Mechanics
• /
• v.12 no.5
• /
• pp.527-540
• /
• 2001

A new sort of learning algorithm named whole learning algorithm is proposed to simulate the nonlinear and dynamic behavior of RC members for the estimation of structural integrity. A mathematical technique to solve the multi-objective optimization problem is applied for the learning of the feedforward neural network, which is formulated so as to minimize the Euclidean norm of the error vector defined as the difference between the outputs and the target values for all the learning data sets. The change of the outputs is approximated in the first-order with respect to the amount of weight modification of the network. The governing equation for weight modification to make the error vector null is constituted with the consideration of the approximated outputs for all the learning data sets. The solution is neatly determined by means of the Moore-Penrose generalized inverse after summarization of the governing equation into the linear simultaneous equations with a rectangular matrix of coefficients. The learning efficiency of the proposed algorithm from the viewpoint of computational cost is verified in three types of problems to learn the truth table for exclusive or, the stress-strain relationship described by the Ramberg-Osgood model and the nonlinear and dynamic behavior of RC members observed under an earthquake.

• Journal of Information Technology Applications and Management
• /
• v.23 no.1
• /
• pp.33-43
• /
• 2016

Along with the spread of digital music and recent growth in the digital music industry, the demands for music recommender are increasing. These days, listeners have increasingly preferred to digital real-time streamlining and downloading to listen to music because it is convenient and affordable for the listeners to do that. We use Bayesian learning through weight of listener's prefered music site such as Melon, Billboard, Bugs Music, Soribada, and Gini. We reflect most popular current songs across all genres and styles for music recommender system using user profile. It is necessary for us to make the task of preprocessing of clustering the preference with weight of listener's preferred music site with popular music charts. We evaluated the proposed system on the data set of music sites to measure its performance. We reported some of the experimental result, which is better performance than the previous system.

• Journal of Korea Multimedia Society
• /
• v.21 no.4
• /
• pp.441-449
• /
• 2018

Deep learning has been used for various processing centered on image recognition. One core algorithms of the deep learning, convolutional neural network is an deep neural network that specialized in image recognition. In this paper, we use a convolutional neural network to classify forest insects and propose an optimization method. Experiments were carried out by combining two weight initialization and six parameter update methods. As a result, the Xavier-SGD method showed the highest performance with an accuracy of 82.53% in the 12 different combinations of experiments. Through this, the latest learning algorithms, which complement the disadvantages of the previous parameter update method, we conclude that it can not lead to higher performance than existing methods in all application environments.