• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.5
• /
• pp.477-481
• /
• 2015

Implementation of memristor-based multilayer neural networks and their hardware-based learning architecture is investigated in this paper. Two major functions of neural networks which should be embedded in synapses are programmable memory and analog multiplication. "Memristor", which is a newly developed device, has two such major functions in it. In this paper, multilayer neural networks are implemented with memristors. A Random Weight Change algorithm is adopted and implemented in circuits for its learning. Its hardware-based learning on neural networks is two orders faster than its software counterpart.

• Journal of the Korean School Mathematics Society
• /
• v.13 no.3
• /
• pp.345-356
• /
• 2010

Variables and expressions are essential for doing mathematics. Especially abbreviations of the multiplication sign ${\times}$ and the division sign ${\div}$ are current rules that we usually follow. In this paper, we devised a Card-Game for exercising abbreviations of the multiplication sign ${\times}$ and the division sign ${\div}$ in calculating expressions, designed a teaching unit for the calculation of expressions using the Card-Game in the variables and expressions strand, and discussed the implications of using the Card-Game for motivating students, cooperative learning, diagnosis and correction of errors, and so on.

• Journal of the Korean School Mathematics Society
• /
• v.14 no.4
• /
• pp.477-490
• /
• 2011

The concept of pedagogical content knowledge (PCK) has been developed and expanded to identify essential components of mathematical knowledge for teaching (MKT) by Ball and her colleagues (2008). This study proposes an alternative perspective to view MKT focusing on key developmental understandings (KDUs) that carry through an instructional sequence, that are foundational for learning other ideas. In this study we provide constructive components of KDUs in fraction multiplication by focusing on the constructs of 'three-level-of-units structure' and 'recursive partitioning operation'. Expecially, our participating preservice elementary teacher, Jane, demonstrated that recursive partitioning operations with her length model played a significant role as a KDU in fraction multiplication.

• Proceedings of the KIEE Conference
• /
• 1994.11a
• /
• pp.326-328
• /
• 1994

A modified Kohonen's simple Competitive Learning(SCL) algorithm which has binary reinforcement function and a constant adaptation gain is proposed. In contrast to the time-varing adaptation gain of the original Kohonen's SCL algorithm, the proposed algorithm uses a constant adaptation gain, and adds a binary reinforcement function in order to compensate for the lowered learning ability of SCL due to the constant adaptation gain. Since the proposed algorithm does not have the complicated multiplication, it's digital hardware implementation is much easier than one of the original SCL.

• Journal of Information Technology Applications and Management
• /
• v.16 no.1
• /
• pp.137-148
• /
• 2009

Knowledge management becomes the key point for organizations to survive and maintain competitive advantages in the knowledge economy era. E-learning plays a vital role for the organizational learning. How to share the experience of knowledge and the success of the knowledge management has great connection with the organizational culture. This study focuses on the factors of effective E-learning as well as its relation to the organizational culture. A successful e-learning system should not only aim at different statistical variables but emphasize on : course contents, variety of teaching methods and establishes a stable network environment. A stable E-learning platform and speedy bandwidth is a must to achieve the non-barrier communication and built an interactive learning environment. To achieve success in E-learning, it is not necessary to divide the organizational culture to strengthen the course content multiplication and plans the E-learning supervisory work by the sole responsibility unit. It should establish an ample teaching frequency width and platform and also must establish the appropriate study network frequency width and hardware equipment to achieve the best E-learning effect. The interaction in different organizational culture in adapting E-learning, those Ad-hoc and Marketing Culture, are mostly influence by the external environment and have more interactive content. Those in Clan and Hierarchy Culture are affected by traditional conception and lack of interaction. Meanwhile, under the cost consideration, Clan and Ad-hoc Culture on the dynamic side prefer to spend more cost on E-Learning while the stable side, Hierarchy and Marketing culture are willing to pay more expenses on E-Learning.

• The Mathematical Education
• /
• v.48 no.3
• /
• pp.353-358
• /
• 2009

The article discusses the independence concept occurring in the learning of probability. The author does not distinguishes the independence in the events from the independence in the trials. Instead, the author suggests the physico-empirical independence and the logico-mathematical independence to distinguish between the two concepts.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.373-377
• /
• 2018

In this paper, we propose an implementation of a neural network accelerator for reducing the rendering noise using OpenCL. Among the rendering algorithms, we selects a ray tracing to assure a high quality graphics. Ray tracing rendering uses ray to render, less use of the ray will result in noise. Ray used more will produce a higher quality image but will take operation time longer. To reduce operation time whiles using fewer rays, Learning Base Filtering algorithm using neural network was applied. it's not always produce optimize result. In this paper, a new approach to Matrix Multiplication that is based on General Matrix Multiplication for improved performance. The development environment, we used specialized in high speed parallel processing of OpenCL. The proposed architecture was verified using Kintex UltraScale XKU6909T-2FDFG1157C FPGA board. The time it takes to calculate the parameters is about 1.12 times fast than that of Verilog-HDL structure.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.7
• /
• pp.211-218
• /
• 1994

Stochastic computation employs random pulse streams to represent numbers. In this paper, we study a new method to implement the number system which uses the ratio of the numbers of ones and zeros in the pulse streams. In this number system. if P is the probability that a pulse is one in a pulse stream then the number X represented by the pulse stream is defined as P/(1-P). We propose circuits to implement the basic operations such as addition multiplication and sigmoid function with this number system and examine the error characteristics of such operations in stochastic computation. We also propose a neuron model and derive a learning algorithm based on backpropagation for the 3-layered feedforward neural networks. We apply this learning algorithm to a digit recognition problem. To analyze the results, we discuss the errors due to the variance of the random pulse streams and the quantization noise of finite length register.

• Research in Mathematical Education
• /
• v.17 no.4
• /
• pp.221-241
• /
• 2013

The data for the present paper was a part of a large research project conducted to assess preservice teachers' knowledge related to fractions and place value at a southwestern public university in 2007. The study utilized convenience sampling, consisting of 150 elementary preservice teachers who were enrolled in a mathematics methods course before their student teaching. The results demonstrated preservice teachers' knowledge of teaching comparison, addition, subtraction, and multiplication of fractions was insufficient even though these should be basic knowledge. Teacher preparation programs should emphasize profound knowledge for teaching fractions using representations.

• Korean Journal of Child Studies
• /
• v.23 no.6
• /
• pp.33-47
• /
• 2002

This study examined the effects of conditions of generation(0, 1, or 2 cognitive operations) and task difficulty in children's recall. Subjects were 40 children in each age group, 8-year-olds and 10-year-olds. Each subject was shown 12 simple or difficult multiplication problems in one of the conditions of generation. After a buffer task, subjects were required to recall correct answers to the problems in random order. The data were analyzed by ANOVA and simple main effect analyses. Results showed that generation effect(GE) occurred among children younger than 12, and GE improved with age. Learning from cognitive operations was more effective than learning through simple repetition. Easier tasks led to greater GE, a phenomenon explained by procedures used in this study.