• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.163-167
• /
• 2000

The eligibility is used to solve the credit-assignment problem which is one of important problems in reinforcement learning. Conventional eligibilities which are accumulating eligibility and replacing eligibility make ineffective use of rewards acquired in learning process. Because only an executed action in a visited state is learned by these eligibilities. Thus, we propose a new eligibility, called the weighted eligibility with which not only an executed action but also neighboring actions in a visited state are to be learned. The fuzzy Q-learning algorithm using proposed eligibility is applied to a cart-pole balancing problem, which shows improvement of learning speed.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.2
• /
• pp.28-37
• /
• 1999

Differentially Responsible Adaptive Critic Learning technique is proposed for learning the control technique with multiple control inputs as in robot system using reinforcement learning. The reinforcement learning is a self-learning technique which learns the control skill based on the critic information Learning is a after a long series of control actions. The Adaptive Critic Learning (ACL) is the representative reinforcement learning structure. The ACL maximizes the learning performance using the two learning modules called the action and the critic modules which exploit the external critic value obtained seldomly. Drawback of the ACL is the fact that application of the ACL is limited to the single input system. In the proposed Differentially Responsible Action Dependant Adaptive Critic learning structure, the critic function is constructed as a function of control input elements. The responsibility of the individual control action element is computed based on the partial derivative of the critic function in terms of each control action element. The proposed learning structure has been constructed with the CMAC neural networks and some simulations have been done upon the two dimensional Cart-Role system and robot squatting problem. The simulation results are included.

• The Journal of Korean Philosophical History
• /
• no.28
• /
• pp.331-362
• /
• 2010

Simjae defined the relationship between Learning of Classics and Learning of the Mind-and-Heart as mutually interdependent. Clarifying "righteousness and principle" lies within the purview of "knowledge" and cultivating the mind-and-heart based on such knowledge lies within the realm of "action." Learning of Classics and Learning of Controlling the Mind-and-Heart thus can be understood as relationship between knowledge and action. If Simjae's theory of knowledge and action is applied to the relationship between Learning of Classics and Learning of the Mind-and-Heart, we can derive the following conclusion. His assertion that "knowledge precedes action" indicates that classical studies to explore the principle of goodness must precede mind-and-heart studies to cultivate the mind. In fact, only when we know what is the right principle can we cultivate our mind based on that principle. However, Simjae attached importance to action in terms of its significance. This means that the Learning of the Mind-and-Heart is "eventually more important" than the Learning of Classics which explores the principle of goodness. Thus, when linked to his theory on knowledge and action, Simjae 's philosophy founded on the twin pillars of classical studies and mind-and-heart studies can be summarized: "One must first delve into the principle of goodness through Confucian classical studies and then rectify one's mind based on knowledge thus gained."

• Journal of the Korean Society of Physical Medicine
• /
• v.5 no.3
• /
• pp.395-404
• /
• 2010

Purpose : The object of this study was to examine the effect of motor learning on brain activation depending on the method of motor learning. Methods : The brain activation was measured in 9 men by fMRI. The subjects were divided into the following groups depending on the method of motor learning: actually practice (AP, n=3) group, action observation (AO, n=3) group and motor imagery (MI, n=3) group. In order to examine the effect of motor learning depending on the method of motor learning, the brain activation data were measured during learning. For the investigation of brain activation, fMRI was conducted. Results : The results of brain activation measured before and during learning were as follows; (1) During learning, the AP group showed the activation in the following areas: primary motor area located in precentral gyrus, somatosensory area located in postcentral gyrus, supplemental motor area and prefrontal association area located in precentral gyrus, middle frontal gyrus and superior frontal gyrus, speech area located in superior temporal gyrus and middle temporal gyrus, Broca's area located in inferior parietal lobe and somatosensory association area of precuneus; (2) During learning, the AD groups showed the activation in the following areas: primary motor area located in precentral gyrus, prefrontal association area located in middle frontal gyrus and superior frontal gyrus, speech area and supplemental motor area located in superior temporal gyrus and middle temporal gyrus, Broca's area located in inferior parietal lobe, somatosensory area and primary motor area located in precentral gyrus of right cerebrum and left cerebrum, and somatosensory association area located in precuneus; and (3) During learning, the MI group showed activation in the following areas: speech area located in superior temporal gyrus, supplemental area, and somatosensory association area located in precuneus. Conclusion : Given the results above, in this study, the action observation was suggested as an alternative to motor learning through actual practice in serial reaction time task of motor learning. It showed the similar results to the actual practice in brain activation which were obtained using activation of mirror neuron. This result suggests that the brain activation occurred by the activation of mirror neuron, which was observed during action observation. The mirror neurons are located in primary motor area, somatosensory area, premotor area, supplemental motor area and somatosensory association area. In sum, when we plan a training program through physiotherapy to increase the effect during reeducation of movement, the action observation as well as best resting is necessary in increasing the effect of motor learning with the patients who cannot be engaged in actual practice.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• Korean journal of medical education
• /
• v.30 no.4
• /
• pp.295-308
• /
• 2018

Purpose: Although medical curricula are now better structured for integration of biomedical sciences and clinical training, most teaching and learning activities still follow the older teacher-centric discipline-specific formats. A newer pedagogical approach, known as Collaborative Learning Cases (CLCs), was adopted in the medical school to facilitate integration and collaborative learning. Before incorporating CLCs into the curriculum of year 1 students, two pilot runs using the action research method was carried out to improve the design of CLCs. Methods: We employed the four-phase Kemmis and McTaggart's action research spiral in two cycles to improve the design of CLCs. A class of 300 first-year medical students (for both cycles), 11 tutors (first cycle), and 16 tutors (second cycle) were involved in this research. Data was collected using the 5-points Likert scale survey, open-ended questionnaire, and observation. Results: From the data collected, we learned that more effort was required to train the tutors to understand the principles of CLCs and their role in the CLCs sessions. Although action research enables the faculty to improve the design of CLCs, finding the right technology tools to support collaboration and enhance learning during the CLCs remains a challenge. Conclusion: The two cycles of action research was effective in helping us design a better learning environment during the CLCs by clarifying tutors' roles, improving group and time management, and meaningful use of technology.

• Korean System Dynamics Review
• /
• v.15 no.4
• /
• pp.129-159
• /
• 2014

This Study discuss exploring normative-prescriptive factors after the themes on Organizational learning categorize two descriptive/explanatory-perspectives, prescriptive/normative dimension. The former would contain information processing model, theory of action, organizing in organization, while Senge's suggestion on Learning Organization may compose the latter. Each perspective is reconstructed and reinterpreted into the causal mapping relationship founded on system thinking and SD. Underlying on the former try to discovery validities of the latter. But this study only put forward the integral-dynamic model of organizational learning without empirical simulation.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.47-52
• /
• 2022

The purpose of this study is to confirm the effect of nursing process education applying action learning on the critical thinking tendency, self-leadership, and self-directed learning ability of nursing college students. A total of 96 subjects were studied, and data collection was from September to December 2021. For data analysis, the frequency, percentage, and corresponding sample t-test were used using spss/win 23. Results show that self-directed learning ability(t=-3.76, p<.001) was significantly improved. In addition, critical thinking disposition and self-leadership(r=.730, p<.001), critical thinking disposition and self-directed learning ability (r=.701, p<.001), self-leadership and self-directed learning ability(r=.734 p<.001) had a statistically significant positive correlation between them. As a result of this study, it can be seen that the nursing course education applied to action learning has a positive effect on the self-directed learning ability of nursing college students. In the future, research is needed to confirm the effects of various teaching and learning methods.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1147-1148
• /
• 2008

In this paper, we propose action-learning method based on teaching. By adopting this method, we can handle an exception case which cannot be handled in an Ethology-based Action SElection mechanism. Our proposed method is verified by employing AIBO robot as well as EASE platform.

• Information Systems Review
• /
• v.8 no.1
• /
• pp.287-303
• /
• 2006

Recently, Investment on HRM, particularly, on training and development, in companies has been increased. Therefore, HR managers pay attention to action learning that has the practical effect on performance. The purpose of this study is to introduce action learning as an efficient training method and simultaneously to raise operational issues from the case study. This study analyses a training and development program applying action learning for team manager candidates in corporate Hyosung from September, 2005 to January, 2006. The findings are as follows: First, inefficient processes are thrown out by the process reengineering applying action learning. Second, the training and development activity is maximized by the integrated use of internal and external facilitators. Third, the steady support of executives and the driving force of HRD managers are considered as main success factors.