• Journal of Korea Multimedia Society
• /
• v.9 no.5
• /
• pp.649-657
• /
• 2006

Reinforcement Learning is a computational approach to learning whereby an agent take an action which maximize the total amount of reward it receives among possible actions within current state when interacting with a uncertain environment. Q-learning, one of the most active algorithm in Reinforcement Learning, is consist of rewards which is obtained when an agent take an action. But it has the problem with mapping real world to discrete states. When state spaces are very large, Q-learning suffers from time for learning. In constant, when the state space is reduced, many state spaces map to single state space. Because an agent only learns single action within many states, an agent takes an action monotonously. In this paper, to reduce time for learning and complement simple action, we propose the Q-learning using influence map(QIM). By using influence map and adjacent state space's learning result, an agent could choose proper action within uncertain state where an agent does not learn. When this paper compares simulation results of QIM and Q-learning, we show that QIM effects as same as Q-learning even thought QIM uses 4.6% of the Q-learning's state spaces. This is because QIM learns faster than Q-learning about 2.77 times and the state spaces which is needed to learn is reduced, so the occurred problem is complemented by the influence map.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.4
• /
• pp.350-356
• /
• 1997

It is desirable for autonomous robot systems to possess the ability to behave in a smooth and continuous fashion when interacting with an unknown environment. Although Q-learning requires a lot of memory and time to optimize a series of actions in a continuous state space, it may not be easy to apply the method to such a real environment. In this paper, for continuous state space applications, to solve problem and a triangular type Q-value model\ulcorner This sounds very ackward. What is it you want to solve about the Q-value model. Our learning method can estimate a current Q-value by its relationship with the neighboring states and has the ability to learn its actions similar to that of Q-learning. Thus, our method can enable robots to move smoothly in a real environment. To show the validity of our method, navigation comparison with Q-learning are given and visual tracking simulation results involving an 2-DOF SCARA robot are also presented.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.428-432
• /
• 2005

This paper has studied the concept and technical factors of e-Learning system to which we intend to apply domestic biodiversity information. This article describes how we analyzed and designed the e-learning system to serve biodiversity information as e-Learning contents. It would be useful for the public and students if this information are organized and provided as e-learning contents especially in our country which has well-established network infrastructure considering the limited land space. It is expected that the establishment of e-Learning system based on this proposed design will help students and public to access and team biodiversity on cyber space.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1005-1008
• /
• 1993

Supervised learnmg 01 recurrent neural networks (RNNs) is discussed. First, we review the present state of art, featuring their major properties in contrast of those of the multilayer neural networks. Then, we concisely describe one of the most practical learning algorithms, i.e. backpropagation through time. Revising the basic formulation of the learning algorithms, we derive a general formula to solve for the exact solution(s) of the whole connection weights w of RNNs. On this basis we introduce a novel interpretation of the supervised learning. Namely, we define a multidimensional Euclidean space, by assigning the cost function E(w) and every component of w to each coordinate axis. Since E=E(w) turns up as a hyper surface in this space, we refer to the surface as learning surface. We see that topological features of the learning surface are valleys and hills. Finally, after explicating that the numerical procedures of learning are equivalent to descending slopes of the learning surface along the steepest gradient, we show that a minimal value of E(w) is the intersection of curved valleys.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.158-163
• /
• 2024

Virtual world technology is driving major advances in education, entertainment, and professional training. Metaverse and extended reality (XR) technologies maximize immersion to enhance learning, provide global learning environments, and expose students to situations that are difficult to experience in real life. Career exploration is an important developmental task in adolescence, and virtual training maximizes learning by providing life-like experiences with imagery training. Virtual training overcomes spatial, financial, performance, and situational constraints and is effective in a variety of fields, including military and disaster training. It provides customized learning for various users such as youth, job seekers, and people with disabilities, deepening their understanding of professional activities and improving their problem-solving skills. It also improves the quality of learning through repetitive learning and contributes to the improvement of teamwork and communication skills, and helps to solve financial problems by using unlimited internal resources and space in virtual space, and enables people with disabilities to perform in various professions. This paper investigated the value of virtual training as a comprehensive educational tool through an economical and efficient learning experience.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.668-676
• /
• 2016

This study reviewed the planning characteristics of contemporary Japanese middle school architecture on which related studies are insufficient, aiming to obtain new ideas for planning Korean middle school facilities. Fourteen case schools built after 1990s were selected and analyzed. They were divided into learning-living space and other major spaces. The planning characteristics of the case schools are summarized as follows 1) The case schools were classified into two categories, departmentalized classroom type (D type) and usual with variation type (UV type) by school system. These categories can also be the classification standard for basic architectural characteristics in learning and living space of case schools. 2) D type case schools have departmentalized classrooms, home base, media space and teacher's space for learning-living space. D type case schools are divided into 'attached-to-classroom type' and 'separate type' depending on the adjacency of the home base and departmentalized classroom. 3) UV type case schools have multipurpose space around the classroom for learning-living space and can be divided into two types, i.e., 'directly adjacent' and 'separate', depending on the connectivity to classroom of multipurpose room. 4) Specialized classrooms are designed to have the openness to the public and the own characteristics of school subjects strengthened and show the spatial differentiation with connected ancillary spaces. 5) Libraries are designed as complex zones grouped with computer labs, audio visual rooms and multipurpose halls not as a single room and as open plan not with a closed wall. 6) The gymnasium is the basic sports facility with a martial arts room and outdoor pool, which are for after-school activities as well as physical education class. 7) The terrace, balcony and outdoor stairs are frequently used architectural vocabularies as diverse outdoor spaces with a variety of functions.

• Journal of KIISE:Software and Applications
• /
• v.29 no.9
• /
• pp.654-668
• /
• 2002

In this paper, we present an empirical study for improving the Korean text chunking based on machine learning and feature set selection approaches. We focus on two issues: the problem of selecting feature set for Korean chunking, and the problem of alleviating the data sparseness. To select a proper feature set, we use a heuristic method of searching through the space of feature sets using the estimated performance from a machine learning algorithm as a measure of "incremental usefulness" of a particular feature set. Besides, for smoothing the data sparseness, we suggest a method of using a general part-of-speech tag set and selective lexical information under the consideration of Korean language characteristics. Experimental results showed that chunk tags and lexical information within a given context window are important features and spacing unit information is less important than others, which are independent on the machine teaming techniques. Furthermore, using the selective lexical information gives not only a smoothing effect but also the reduction of the feature space than using all of lexical information. Korean text chunking based on the memory-based learning and the decision tree learning with the selected feature space showed the performance of precision/recall of 90.99%/92.52%, and 93.39%/93.41% respectively.

• Journal of KIISE:Software and Applications
• /
• v.30 no.11
• /
• pp.1054-1061
• /
• 2003

Q-Learning, a representative algorithm of reinforcement learning, experiences repeatedly until estimation values about all state-action pairs of state space converge and achieve optimal policies. When the state space is high dimensional or continuous, complex reinforcement learning tasks involve very large state space and suffer from storing all individual state values in a single table. We introduce Q-Map that is new function approximation method to get classified policies. As an agent learns on-line, Q-Map groups states of similar situations and adapts to new experiences repeatedly. State-action pairs necessary for fine control are treated in the form of rule. As a result of experiment in maze environment and mountain car problem, we can achieve classified knowledge and extract easily rules from Q-Map

• Journal of the Korean Institute of Educational Facilities
• /
• v.27 no.3
• /
• pp.3-14
• /
• 2020

The purpose of this study is to discuss the planning direction of educational spaces to support children's healthy and creative learning based on bio_philic theory. This study analyzed the characteristics of the application of biophilic patterns in children's education space through case analysis. The conclusion of this study is summarized as follows. As a result of the analysis of children's classroom space, the pattern of 'A(Visual connection with nature), F(Dynamic & Diffuse Light), K(Prospect)' shows high application rate, but the pattern of 'C(Non-Rhythmic Sensory Stimuli), G(Connection with Natural Systems), I(Material Connection with Nature)' shows low application rate. In particular, there is a lack of connection with patterns such as hearing, smell, touch, taste stimulation and water experience, and curiosity through exploration of nature about 'B(Non-visual connection with nature), E(Presence of Water), N(Risk/Peril)' changes in nature and ecosystem. In the corridor and rest space, the pattern of 'A(Visual connection with nature), D(Thermal & Airflow Variability), F(Dynamic & Diffuse Light), G(Connection with Natural Systems), K(Prospect)' shows high application rate, but 'B(Non-visual connection with nature)' shows low application rate. In addition, the application of patterns related to the stimulation of curiosity through direct exploration of nature and the exploration of the patterns of 'E(Presence of Water), N(Risk/Peril)' is insufficient. Therefore, in the case of classroom spaces, the active use of nature as it is should be considered within the scope that does not cause visual confusion, and it should provide an area that can be experienced through the five senses. And corridors and rest spaces should be designed to introduce more active natural elements as spaces to recover stress caused by learning. In other words, the characteristics of children's education facilities need to be connected between classroom space, corridor, rest space and external space. This study is meaningful in that it analyzes and derives the application characteristics of 'biophilic design' which affects the 'Attention Restoration' of children's educational spaces through foreign cases.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1001-1007
• /
• 2020

In recent years, machine learning algorithms are continuously being used and expanded in various fields, such as facial recognition, signal processing, personal authentication, and stock prediction. In particular, various algorithms, such as deep learning, reinforcement learning, and Q-learning, are continuously being improved. Among these algorithms, the expansion of deep learning is rapidly changing. Nevertheless, machine learning algorithms have not yet been applied in several fields, such as personal authentication technology. This technology is an essential tool in the digital information era, walking recognition technology as promising biometrics, and technology for solving state-space problems. Therefore, algorithm technologies of deep learning, reinforcement learning, and Q-learning, which are typical machine learning algorithms in various fields, such as agricultural technology, personal authentication, wireless network, game, biometric recognition, and image recognition, are being improved and expanded in this paper.