• The Transactions of the Korea Information Processing Society
• /
• v.6 no.3
• /
• pp.633-640
• /
• 1999

Reinforcement learning performs learning through interacting with trial-and-error in dynamic environment. Therefore, in dynamic environment, reinforcement learning method like Q-learning and TD(Temporal Difference)-learning are faster in learning than the conventional stochastic learning method. However, because many of the proposed reinforcement learning algorithms are given the reinforcement value only when the learning agent has reached its goal state, most of the reinforcement algorithms converge to the optimal solution too slowly. In this paper, we present COMREL(COMpressed REinforcement Learning) algorithm for finding the shortest path fast in a maze environment, select the candidate states that can guide the shortest path in compressed maze environment, and learn only the candidate states to find the shortest path. After comparing COMREL algorithm with the already existing Q-learning and Priortized Sweeping algorithm, we could see that the learning time shortened very much.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1738-1764
• /
• 2019

With the advent of big data, deep learning technology has become an important research direction in the field of machine learning, which has been widely applied in the image processing, natural language processing, speech recognition and online advertising and so on. This paper introduces deep learning techniques from various aspects, including common models of deep learning and their optimization methods, commonly used open source frameworks, existing problems and future research directions. Firstly, we introduce the applications of deep learning; Secondly, we introduce several common models of deep learning and optimization methods; Thirdly, we describe several common frameworks and platforms of deep learning; Finally, we introduce the latest acceleration technology of deep learning and highlight the future work of deep learning.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.571-585
• /
• 2021

Applications for object detection are expanding as it is automated through artificial intelligence-based processing, such as deep learning, on a large volume of images and videos. High dependence on training data and a non-transparent way to find answers are the common characteristics of deep learning. Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. This paper summarizes the security issues that need to be addressed for future applications and analyzes the state-of-the-art security studies related to robustness, privacy, and integrity of object detection for images and videos.

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.641-644
• /
• 2006

e-learning에서 m-learning으로 진행함에 따라 기존에 사용하던 PDA, Notebook 이 아닌 일반 사용자들이 대부분 가지고 있는 휴대폰을 학습도구로 이용, 다양한 형식의 e-learning contents를 m-learning contents로 변환 활용하기 위하여 화면 capture 기법을 활용하고 무선통신망을 배제하고 유선통신망을 이용하여 서비스 할 수 있는 모델을 제시한다.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.967-985
• /
• 2019

Bug report processing is a key element of bug fixing in modern software maintenance. Bug reports are not processed immediately after submission and involve several processes such as bug report deduplication and bug report triage before bug fixing is initiated; however, this method of bug fixing is very inefficient because all these processes are performed manually. Software engineers have persistently highlighted the need to automate these processes, and as a result, many automation techniques have been proposed for bug report processing; however, the accuracy of the existing methods is not satisfactory. Therefore, this study focuses on surveying to improve the accuracy of existing techniques for bug report processing. Reviews of each method proposed in this study consist of a description, used techniques, experiments, and comparison results. The results of this study indicate that research in the field of bug deduplication still lacks and therefore requires numerous studies that integrate clustering and natural language processing. This study further indicates that although all studies in the field of triage are based on machine learning, results of studies on deep learning are still insufficient.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.500-501
• /
• 2019

In the $4^{th}$ generation industry, self-directed learning is very important than Injection learning. Therefore many educational institutions has developed method of self-directed learning. In order for self-directed learning to be effective, it is more important for faculty to manage the overall process of learning rather than being directly involved in the student's academic work. Therefore, learning counseling is an important way to effectively carry out self-directed learning. In this paper, we analyze the status of open data for natural language processing that can implement the learning consultation contents so that various applications can be done through natural language processing.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.10
• /
• pp.673-684
• /
• 2003

In order to understand the concepts of image processing with effect, a learning system with an actual practice is necessary. As most image processing learning materials have some inconvenient respects that it is difficult to understand the processing procedure because they simply show the processed results as figures in the contents, and also, a separate practice tool is needed to operate the source codes because they provide the program source codes as a part in the context. In this paper, in order to solve above inconvenient respects, an image processing learning system that be able to improve the learning effects as accomplishing the theory studying and the actual practice in parallel is proposed. As this system is composed on the bases of java, it is independent to the platforms and it is possible to implement on the Web.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.533-534
• /
• 2019

This paper is to summarize the academic status of deep learning in Chinese scientific institutions and universities based on the literatures from CNKI. We analyzed the various development of deep learning in China based on the application of computer vision, voice recognition and natural language processing.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.12
• /
• pp.1-7
• /
• 2021

The deep learning image processing technique was used to prevent accidents in lathe work caused by worker negligence. During lathe operation, when the chuck is rotated, it is very dangerous if the operator's hand is near the chuck. However, if the chuck is stopped during operation, it is not dangerous for the operator's hand to be in close proximity to the chuck for workpiece measurement, chip removal or tool change. We used YOLO (You Only Look Once), a deep learning image processing program for object detection and classification. Lathe work images such as hand, chuck rotation and chuck stop are used for learning, object detection and classification. As a result of the experiment, object detection and class classification were performed with a success probability of over 80% at a confidence score 0.5. Thus, we conclude that the artificial intelligence deep learning image processing technique can be effective in preventing incidents resulting from worker negligence in future manufacturing systems.