• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.1
• /
• pp.32-42
• /
• 2000

This paper presents an on-line learning algorithm for sequential construction of generalized radial basis function networks (GRBFNs) to model nonlinear systems from empirical data. The GRBFN, an extended from of standard radial basis function (RBF) networks with constant weights, is an architecture capable of representing nonlinear systems by smoothly integrating local linear models. The proposed learning algorithm has a two-stage learning scheme that performs both structure learning and parameter learning. The structure learning stage constructs the GRBFN model using two construction criteria, based on both training error criterion and Mahalanobis distance criterion, to assign new hidden units and the linear local models for given empirical training data. In the parameter learning stage the network parameters are updated using the gradient descent rule. To evaluate the modeling performance of the proposed algorithm, simulations and their results applied to two well-known benchmarks are discussed.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.253-263
• /
• 2021

Machine learning is the process of constructing a cost function using learning data used for learning and an artificial neural network to predict the data, and finding parameters that minimize the cost function. Parameters are changed by using the gradient-based method of the cost function. The more complex the digital signal and the more complex the problem to be learned, the more complex and deeper the structure of the artificial neural network. Such a complex and deep neural network structure can cause over-fitting problems. In order to avoid over-fitting, a weight decay regularization method of parameters is used. We additionally use the value of the cost function in this method. In this way, the accuracy of machine learning is improved, and the superiority is confirmed through numerical experiments. These results derive accurate values for a wide range of artificial intelligence data through machine learning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.13-19
• /
• 2019

The accuracy of machine learning is greatly affected by amount of learning data and quality of data. Collecting existing Web-based learning data has danger that data unrelated to actual learning can be collected, and it is impossible to secure data transparency. In this paper, we propose a method for collecting data directly in parallel by blocks in a block - chain structure, and comparing the data collected by each block with data in other blocks to select only good data. In the proposed system, each block shares data with each other through a chain of blocks, utilizes the All-reduce structure of Parallel-SGD to select only good quality data through comparison with other block data to construct a learning data set. Also, in order to verify the performance of the proposed architecture, we verify that the original image is only good data among the modulated images using the existing benchmark data set.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.118-120
• /
• 2009

In this paper, we present the Q-learning method for adaptive traffic signal control on the basis of multi-agent technology. The structure is composed of sixphase agents and one intersection agent. Wireless communication network provides the possibility of the cooperation of agents. As one kind of reinforcement learning, Q-learning is adopted as the algorithm of the control mechanism, which can acquire optical control strategies from delayed reward; furthermore, we adopt dynamic learning method instead of static method, which is more practical. Simulation result indicates that it is more effective than traditional signal system.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.1
• /
• pp.153-159
• /
• 2017

In recent years there has been a rise in the use and interest of the flipped learning as a teaching and learning paradigm. The flipped learning model includes any use of Internet technology to enrich the learning in a classroom, so that a professor can spend more time interacting with students instead of lecturing. In the flipped model, students viewed video lectures online outside of class time. Students then performed two kinds of assignments, a teamwork assignment and an individual work assignment, through the class time. In this paper, we propose a flipped educational model for a college class. This experimental research compares class of college algorithm using the flipped classroom methods and the traditional lecture-homework structure and its effect on student achievement. The result data of mid-term exam and final exam were analyzed and compared with previous year data. The findings of this research show that there was not a significant difference in the scores of student between two lecturing methods. The survey result and lecture evaluation by students show that students are in favor of the flipped learning.

• International Journal of Advanced Culture Technology
• /
• v.8 no.2
• /
• pp.176-183
• /
• 2020

This study inquired about the convergence learning program for childhood based on Erikson's play theory and design education for children's behavior development. I analyzed the convergence learning programs of Summer Camps in the Pacific Science Center, Galileo Learning. The contents of the programs show the most used imaginary and symbolic contents that represent the real-world problems which are related design thinking process. The curriculums and structure of the programs are based on the design thinking method and K-12 theory. The visual thinking method and the applications are used for expressing their creativity and approaching the technical skills easily. The play concept theory is an affirmative way to strengthen the children's psychological and social development. Therefore, the convergence learning program should integrate the design thinking process and apply the play concept theory for supporting and developing the children's behavior.

• Journal of Korean Association for Spatial Structures
• /
• v.19 no.1
• /
• pp.93-100
• /
• 2019

There has been considerable recent interest in deep learning techniques for structural analysis and design. However, despite newer algorithms and more precise methods have been developed in the field of computer science, the recent effective deep learning techniques have not been applied to the damage detection topics. In this study, we have explored the structural damage detection method of truss structures using the state-of-the-art deep learning techniques. The deep neural networks are used to train knowledge of the patterns in the response of the undamaged and the damaged structures. A 31-bar planar truss are considered to show the capabilities of the deep learning techniques for identifying the single or multiple-structural damage. The frequency responses and the elasticity moduli of individual elements are used as input and output datasets, respectively. In all considered cases, the neural network can assess damage conditions with very good accuracy.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.112-115
• /
• 2022

The process of deep learning usually needs to deal with massive data which has greatly limited the development of deep learning technologies today. Convolutional Neural Network (CNN) structure is often used to solve image classification problems. However, a large number of images may be required in order to train an image in CNN, which is a heavy burden for existing computer systems to handle. If the image data can be compressed under the premise that the computer hardware system remains unchanged, it is possible to train more datasets in deep learning. However, image compression usually adopts the form of lossy compression, which will lose part of the image information. If the lost information is key information, it may affect learning performance. In this paper, we will analyze the effect of image compression on deep learning performance on CNN-based cat and dog classification. Through the experiment results, we conclude that the compression of images does not have a significant impact on the accuracy of deep learning.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2000.10a
• /
• pp.509-514
• /
• 2000

A structural control algorithm using CMAC(Cerebellar Model Articulation Controller) neural network is proposed Learning rule for CMAC is derived based on cost function. Learning convergence of CMAC is compared with MLNN(Multilayer Neural Network). Numerical examples are shown to verify the proposed control algorithm. Examples show that CMAC can be applicable to structural control with fast learning speed.

• Structural Engineering and Mechanics
• /
• v.47 no.4
• /
• pp.495-511
• /
• 2013

In this paper, a new efficient optimization algorithm called Teaching-Learning-Based Optimization (TLBO) is used for the least weight design of trusses with continuous design variables. The TLBO algorithm is based on the effect of the influence of a teacher on the output of learners in a class. Several truss structures are analyzed to show the efficiency of the TLBO algorithm and the results are compared with those reported in the literature. It is concluded that the TLBO algorithm presented in this study can be effectively used in the weight minimization of truss structures.