• 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.

• East Asian mathematical journal
• /
• v.37 no.3
• /
• pp.333-354
• /
• 2021

A support vector machine (SVM) is a state-of-the-art machine learning model rooted in structural risk minimization. SVM is underestimated with regards to its application to real world problems because of the difficulties associated with its use. We aim at showing that the performance of SVM highly depends on which kernel function to use. To achieve these, after providing a summary of support vector machines and kernel function, we constructed experiments with various benchmark datasets to compare the performance of various kernel functions. For evaluating the performance of SVM, the F1-score and its Standard Deviation with 10-cross validation was used. Furthermore, we used taylor diagrams to reveal the difference between kernels. Finally, we provided Python codes for all our experiments to enable re-implementation of the experiments.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.197-200
• /
• 1996

This paper considers feedback error learning neural networks for robot manipulator control. Feedback error learning proposed by Kawato [2,3,5] is a useful learning control scheme, if nonlinear subsystems (or basis functions) consisting of the robot dynamic equation are known exactly. However, in practice, unmodeled uncertainties and disturbances deteriorate the control performance. Hence, we presents a robust feedback error learning scheme which add robustifying control signal to overcome such effects. After the learning rule is derived, the stability is analyzed using Lyapunov method.

• Communications for Statistical Applications and Methods
• /
• v.15 no.3
• /
• pp.343-351
• /
• 2008

By supervised learning with p predictors, we frequently obtain a prediction function of the form $y\;=\;f(x_1,...,x_p)$. When $p\;{\geq}\;3$, it is not easy to understand the inner structure of f, except for the case the function is formulated as additive. In this study, we propose to use p simple graphs for visual understanding of complex prediction functions produced by several supervised learning engines such as LOESS, neural networks, support vector machines and random forests.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.179-192
• /
• 2014

Keeping in line with the recent changes in the information technology environment, the online learning environment that supports multiple users' participation such as MOOC (Massive Open Online Courses) has become important. One of the largest professional associations in Information Technology, IEEE Computer Society, announced that "Supporting New Learning Styles" is a crucial trend in 2014. Popular MOOC services, CourseRa and edX, have continued to build active learning environment with a large number of lectures accessible anywhere using smart devices, and have been used by an increasing number of users. In addition, collaborative web services (e.g., blogs and Wikipedia) also support the creation of various user-uploaded learning materials, resulting in a vast amount of new lectures and learning materials being created every day in the online space. However, it is difficult for an online educational system to keep a learner' motivation as learning occurs remotely, with limited capability to share knowledge among the learners. Thus, it is essential to understand which materials are needed for each learner and how to motivate learners to actively participate in online learning system. To overcome these issues, leveraging the constructivism theory and collective intelligence, we have developed a social bookmarking system called WeStudy, which supports learning material sharing among the users and provides personalized learning material recommendations. Constructivism theory argues that knowledge is being constructed while learners interact with the world. Collective intelligence can be separated into two types: (1) collaborative collective intelligence, which can be built on the basis of direct collaboration among the participants (e.g., Wikipedia), and (2) integrative collective intelligence, which produces new forms of knowledge by combining independent and distributed information through highly advanced technologies and algorithms (e.g., Google PageRank, Recommender systems). Recommender system, one of the examples of integrative collective intelligence, is to utilize online activities of the users and recommend what users may be interested in. Our system included both collaborative collective intelligence functions and integrative collective intelligence functions. We analyzed well-known Web services based on collective intelligence such as Wikipedia, Slideshare, and Videolectures to identify main design factors that support collective intelligence. Based on this analysis, in addition to sharing online resources through social bookmarking, we selected three essential functions for our system: 1) multimodal visualization of learning materials through two forms (e.g., list and graph), 2) personalized recommendation of learning materials, and 3) explicit designation of learners of their interest. After developing web-based WeStudy system, we conducted usability testing through the heuristic evaluation method that included seven heuristic indices: features and functionality, cognitive page, navigation, search and filtering, control and feedback, forms, context and text. We recruited 10 experts who majored in Human Computer Interaction and worked in the same field, and requested both quantitative and qualitative evaluation of the system. The evaluation results show that, relative to the other functions evaluated, the list/graph page produced higher scores on all indices except for contexts & text. In case of contexts & text, learning material page produced the best score, compared with the other functions. In general, the explicit designation of learners of their interests, one of the distinctive functions, received lower scores on all usability indices because of its unfamiliar functionality to the users. In summary, the evaluation results show that our system has achieved high usability with good performance with some minor issues, which need to be fully addressed before the public release of the system to large-scale users. The study findings provide practical guidelines for the design and development of various systems that utilize collective intelligence.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.4
• /
• pp.815-825
• /
• 2007

The existing web-based self-directed learning systems are in short for the ability of learning skills assessment. Even worse, hey only give test scores as an indicate for test skills, which is also not a good measure for learning skills assessment and makes it difficult to assess learning skills objectively and to present clear assessment criterion. In this paper, we proposed an improved self-directed learning system using fuzzy logic, which can be controlled by learners themselves and helps to evaluate their on learning process. We also implemented the system on the written examination of Engineer Information Processing. The purposed system lust calculates membership functions of learning tine, learning frequency, testing time, and test score. Using them the final membership functions of learning and test skills are calculated and presented in a graphical, i.e. mon understandable, way to user. The purposed system helps learners to assess their achievement and to plan future schedule, and the survey result on the students used the system also supports that.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.686-699
• /
• 2020

In this paper, we propose a supervised-learning-based spatial performance prediction (SLPP) framework for next-generation heterogeneous communication networks (HCNs). Adaptive asset placement, dynamic resource allocation, and load balancing are critical network functions in an HCN to ensure seamless network management and enhance service quality. Although many existing systems use measurement data to react to network performance changes, it is highly beneficial to perform accurate performance prediction for different systems to support various network functions. Recent advancements in complex statistical algorithms and computational efficiency have made machine-learning ubiquitous for accurate data-based prediction. A robust network performance prediction framework for optimizing performance and resource utilization through a linear discriminant analysis-based prediction approach has been proposed in this paper. Comparison results with different machine-learning techniques on real-world data demonstrate that SLPP provides superior accuracy and computational efficiency for both stationary and mobile user conditions.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.35-42
• /
• 2021

The college English teaching-learning model in this study is intended to effectively apply dictogloss activities to enhance competencies such as communication, self-directedness, and cooperation by upgrading the utilization of various online platform functions. Dictogloss is a language teaching and learning activity that combines four functions (listening, speaking, reading, and writing) of communication. College English classes in this study focus on communication-oriented integrated English education. In this study, the teaching and learning is an online-based English integrated teaching-learning method based on constructivism theory. The model presented the roles of learners and teachers according to the seven procedures.

• Philosophy of Education
• /
• no.39
• /
• pp.191-221
• /
• 2009

The aim of this study is to analyse of elements and structure of consciousness theory in the 1887 Psychology written by John Dewey, and to research its educational implications. Conclusions are as follows: Firstly, consciousness theory articulated in first edition of Dewey's Psychology was influenced by neo-Hegelian G. S. Hall, and then characteristics of its theory was metaphysical and idealistic. But after of researching the work of William James, his approach to consciousness changed surprisingly from idealistic to experimental. His experimental approach and scientific attitude to it influenced the formation and development of advanced theories in his epistemology, axiology and pedagogy. Secondly, the structure of consciousness expressed by Dewey has three forms such as knowledge, feeling and will(or volition). This forms are too dynamic and unitary. Dewey considered cognition, feeling, will to be integral functions of each self. The tripartite functions of self, moreover, are unified in will. In other word, will combines subjective feeling and objective knowledge as one self. Will regulates impulse because it powers some stimulus into activity of self. In this view point, his theory of consciousness differs from traditional theories about consciousness for emphasizing dynamic relations and functions. Thirdly, Dewey's theory of consciousness will give some important implications to educational field. It is necessary to fundamental arguments about conscious conditions of learners as a human. For it is impossible to establish some aim of learning, to organize meaningful contents of learning, and also to create some effective methods of learning without consideration of this conditions. And it is important to construct and organize the contents and methods of learning for widening and deepening of educational experiences. Then consciousness and experiences of learners interact each other, so then they will produce some meaningful results of learning in this process.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.117-122
• /
• 2021

Autonomous driving allows cars to drive without people and is being studied very actively thanks to the recent development of artificial intelligence technology. Among artificial intelligence technologies, deep reinforcement learning is used most effectively. Deep reinforcement learning requires us to build a neural network using an appropriate activation function. So far, many activation functions have been suggested, but different performances have been shown depending on the field of application. This paper compares and evaluates the performance of which activation function is effective when using deep reinforcement learning to learn autonomous driving on highways. To this end, the performance metrics to be used in the evaluation were defined and the values of the metrics according to each activation function were compared in graphs. As a result, when Mish was used, the reward was higher on average than other activation functions, and the difference from the activation function with the lowest reward was 9.8%.