KAIST - COMPUTER SCIENCE

  • korea
  • search
  • login

Directions

  • Yeonsu Kim, an undergraduate student of the KAIST ..

    Yeonsu Kim, an undergraduate student of our school, won the best research award of the undergraduate research program (URP) on August 28, 2019 (advisor: Prof. Sung-Ju Lee and research assistant: Taesik Gong). This research is a collaborative work with Prof. Jinwoo Shin at the School of Electrical Engineering and is accepted to an international conference, ACM SenSys: Taesik Gong, Yeonsu Kim, Jinwoo Shin, and Sung-Ju Lee, "MetaSense: Few-Shot Adaptation to Untrained Conditions in Deep Mobile Sensing", In Proceedings of ACM SenSys 2019. They propose a novel method that allows machine learning applications using mobile sensors under ill-posed conditions. Recently, deep learning evolution allows researchers to focus on running various applications on personal mobile devices, for example, diagnosing heart attack using a mobile sensor. However, these deep-learning-based applications have presented suboptimal performance when using untrained personal data or devices. This work encourages more practical mobile sensing applications to be developed.

    ...Read more
  • Sungjun Park, a PH awarded 2019 Google AI Ph.D. Fe..

    https://ai.googleblog.com/2019/09/announcement-of-2019-fellowship.html A Ph.D student Sungjun Park (advisor: Prof. Alice Oh) was awarded the 2019 Google Ph.D. Fellowship in the field of Natural Language Processing (NLP) area. Google has been conducting the Google PhD Fellowship Program from 2009 to spotlight PhD candidates who are doing outstanding work in the field of computer science. The awardees are granted ten thousand dollars worth of scholarship and become connected with Google's specialists each field as mentors to discuss the research and get feedback. This year, a total of fifty Ph.D. students worldwide were awarded, including three Korean students out of ten students in the East Asia. Sungjun Park’s research on Computational Psychotherapy via machine learning (ML) -based NLP has enabled him to award the fellowship. Throughout his PhD years, Sungjun Park proposed to adapt distributed representations, which are generally used in the ML-based NLP area, to Korean. In addition, he presented methods of analyzing trained distributed representation at the annual conference of the association for computational linguistics (ACL) and the conference on empirical methods in natural language processing (EMNLP) in 2017 and 2018, respectively. Recently, he proposed a criteria to classify psychological counseling clients’ utterance according to their factor in the counseling dialogue and presented at the annual conference of the north american chapter of the association for computational Linguistics (NAACL). In addition, he is actively working on artificial neural network-based dialogue model generation, complex emotion extraction and prediction from text, and developing computational psychotherapy application.

    ...Read more
  • Editorial board member of ACM Transactions on Soft..

    Dr. Shin Yoo, a faculty member of School of Computing, KAIST, has been appointed as an editorial board member of ACM Transactions on Software Engineering and Methodology (TOSEM) starting from July 2019. TOSEM is one of two SCI journals in software engineering, along with IEEE Transactions on Software Engineering. TOSEM has the impact factor of 2.516 in JCR 2017, and is currently ranked at the 18th place by Google Scholar among the Software Systems conferences and journals.

    ...Read more
  • 1st place in Cardiac Segmentation and Best Award i..

    Jeon Tae-joon, a Ph.D. and Lee Na-kyung, a master's degree student both from School of Computing at KAIST (Advisor : Professor Kim Dae Young), were awarded the 1st prize in the AI HeLP Challenge performance presentation for automatically dividing right & left vents, left ventricle myocardium, and positive performance presentation. This challenge held at Asan Medical Center in Seoul on March 13 ,organized by the Ministry of Health and Welfare and Asan Medical Center.

    ...Read more
  • Prof. Jeehoon Kang is appointed to our school

    Professor Jeehoon Kang has been appointed to the School of Computing as of February 27, 2019. Professor Jeehoon Kang received his doctorate degree from Seoul National University in 2019 and his major is Concurency, Parallelism, Programming Language, Verification, and his detailed history is as follows. https://cs.kaist.ac.kr/people/view?idx=590&kind=faculty&menu=160 Let's welcome Professor Jeehoon Kang!

    ...Read more
  • 2019 Science and Culture Exhibition Service Capaci..

    The research team KAIST's Smart Science Museum exhibition technology held the first-half workshop of science and culture exhibition services on Feb. 21-22 at the Hyatt Hotel in Seogwipo, Jeju Island. The Science and Culture Exhibition Service project was started in 2018 as a project supported by the Korea Research Foundation. A total of 15 research teams are involved in Smart Science Museum research group, with three teams from KAIST are participating. In School of Computing Professor Han Dong-soo (the head of the research team), Professor Park Jin-ah and Professor Lee Ki-hyuk are participating, and Professor Lee Woo-hoon is participating from the industrial design department. At the workshop, 15 research team’s manager, joint research institutes, the National Museum of Science research team, and officials from the exhibition headquarters of the National Daegu Science Museum participated to announce their 2019 research plans and reflect on their findings in 2018. During the workshop, Lee Jung-mo, director of the Seoul Municipal Science Museum, Kwak Soo-jin, CEO of "The Shake Creative," and Kwon Ki-kyun, CEO of "Science Museum and Culture," attended to give a talk on the science and cultural exhibitions. In addition, a joint advisory meeting was held with advisors for the Science and Culture Exhibition Service Capacity Enhancement Support Project and the research manager of 15 teams. “The workshop was nice because we could exchange information through various research exchanges," said Professor Han Dong-soo. “It was a good place to get hints to strengthen the exhibition capacity of the Korean Science and Culture Exhibition Service," he said

    ...Read more
  • Professor Suk-young Ryu's Award for Excellence and..

    Professor Ryu Suk-young of the School of Computing won the Excellence Award and Professor Kim Joo-ho won the Excellence Award at the Woe School Award, which was held on February 18 to commemorate the 48th anniversary of its foundation. Professor Ryu Seok-young's reward of 5 million won and matching scholarship of 5 million won by alumni Chang Byung-kyu contributed to the School of Computing Scholarship Fund. Congratulation

    ...Read more
  • Professor Kwang-jo Kim selected as Editor of IEEE ..

    Kim Kwang-jo, a professor at the Graduate School of Information Security of School of Computing, was chosen as an editor of IEEE Trans. on Dependable and Secure Computing, an international journal on information protection. This journal is one of 17 journals organized by the IEEE Computing Society, which has an impact factor of 2.926 and H-Index of 56, which bimonthly publishes the latest research results on on basic theories, design methodologies, and mechanisms on design, modeling, and evaluation techniques for systems and networks that provide reliable and security. Professor Kim has been selected as the first generation cryptographer in Korea who has been engaged in research on information protection and cipher since 1982, and is currently a member of the IACR (International Society for Cryptography) stone academy for his excellent research performance and international reputation. [Related Web Page] https://www.computer.org/web/tdsc/about Aims & Scope of the Journal IEEE Transactions on Dependable and Secure Computing (TDSC) publishes archival research results focusing on research into foundations, methodologies, and mechanisms that support the achievement–through design, modeling, and evaluation–of systems and networks that are dependable and secure to the desired degree without compromising performance. The focus also includes measurement, modeling, and simulation techniques, and foundations for jointly evaluating, verifying, and designing for performance, security, and dependability constraints. The IEEE Computer Society sponsors more than 200 technical conferences and events each year, including the industry-oriented "Rock Stars" series, all over the world, aimed at research and industry professionals. Our publications are peer-reviewed, indexed, and authored by technology thought leaders worldwide, and include 17 scholarly journalsand 13 magazinesfeaturing the latest technology trends

    ...Read more
  • Won KSC 2018(Korea Software Congress 2018)

    At KSC 2018 (Korea Software Congress 2018) held from Dec. 19, 2018 (Wed) to Dec. 21(Fri), Pyeongchang, our computer science students won two grand prizes, four excellence awards and one subsidy, as shown. Sincerely congratulates on your award.

    ...Read more
  • Produced Amazon AWS AI Startup Challenge Award and..

    Elice, a programming education startup that was established by KAIST's computer science PhD students, was awarded at AWS AI Startup Challenge hosted by Amazon last year and produced some 80 related talent through data science education management. Elice operates an online programming education platform to effectively manage and operate large-scale computerized education in enterprises or educational institutions. Currently, the online coding platform is provided as a major service by introducing an environment that can be coded online without separate IDE, a free-material code evaluation system that applies grading code intended by professors, a system that prevents cheating, and pair-programming. In recognition of its technical skills, it won the AWS AI Startup Challenge last year, a competition that competes with domestic startups which operate leading technologies and services in the field of artificial intelligence deep learning. In addition, it produced more than 80 talents in related fields last year through an artificial intelligence data science program that has been operating since 2017. The program's faculty consists of KAIST and some of the best scholars in the field of artificial intelligence in Korea. Demo Day, which introduces students' projects, features major Korean IT companies such as Kakao, Naver, Samsung Electronics and LG Electronics, as well as leading startups such as Baemin, K-Mong and Rainist. Park Jin-woo, an engineer at Samsung Electronics who participated in the program, said, "The results of students were better than I thought, and I think it would be a good opportunity for the company if it was connected to recruitment." A trainee said, "It is meaningful that we can get advice on our career path through interviews with a business executive." The program is responsible for creating cases in which past graduates have employed at major IT companies such as Naver, NCsoft, Kakao and PUBG, and for filling the needs of big data talent increased during the 4th Industrial Revolution. An Elice source said, "We will strive to develop technologies to create a smoother programming environment, and we will lower entry barriers and develop curriculums to foster the skills needed by technology companies so that anyone can receive coding education in line with the Fourth Industrial Revolution." Elice is currently actively used by major Korean universities and companies, including KAIST, SK Telecom and Samsung, and recently attracted series A investment from Altos Ventures. [Reference] Students Participated in Data Science Training Promote Project Contents - https://www.youtube.com/channel/UCTok20p3EzAjTJWV8SJM9Gw/videos Elice Academy website - https://academy.elice.io/ Elice Introduction Website - https://elice.io/ [Related article] Data Science Program E-newspaper - http://www.etnews.com/20180925000025 This NewsToday - http://www.enewstoday.co.kr/news/articleView.html?idxno=1233222 Newsworks - http://www.newsworks.co.kr/news/articleView.html?idxno=217042 <Investment Incentive> Asian Economy - http://view.asiae.co.kr/news/view.htm?idxno=2018081309264279730 The Korean Economy - http://news.hankyung.com/article/201808135770j

    ...Read more
  • Software Security Lab of the Graduate School of In..

    The software security research lab (Supervisor : Professor Cha Sang-gil) of the Graduate School of Information Security at School of Computing has handed over 2.8 million won to the department. The software security lab won the Information Protection R&D Data Challenge contest (datachallenge.kr) last November by participating in the auto-detection of vulnerabilities field. Kim Soo-min, Han Hyung-seok, and Choi Jae-seung (Ph.D course), Kim Hong-sik, Oh Dong-hyun, Jeong Min-gyu (Master course), and Cha Sang-kil, who participated in the contest, said they donated 2.8 million won for the development of the School of Computing Choi Jae-seung, the team's representative, said, "Based on the good results at the competition, I think it was the help of the schools and departments that we applied for the study. All of us decided to donate the money in the hope that we would give some back to our juniors, said.

    ...Read more
  • Prime Minister Award

    Professor Daeyoung Kim received a Prime Minister Award for his contributions to Government Innovation, especially in public data strategies. Prof. Kim is a Professor at the KAIST School of Computing. He is also the Director of the Real-time and Embedded Systems Laboratory and the Director of Auto-ID Labs at KAIST. His research interests are Operating Systems, Wireless Network Protocols, (GPGPU) Cloud Computing, and the Internet of Things. He is actively collaborating with numerous international research groups from Universities: MIT, Stanford, Cambridge, UCL, TU Vienna, ETH Zurich, HESSO, U. of Murcia, Keio, Fudan, National Taiwan University of Science and Technology, Adelaide, University of Vale do Rio dos Sinos, Khalifa University, and King Saud University. https://www.yna.co.kr/view/PYH20181226167600013?section=search

    ...Read more
  • Professor Meeyoung Cha was Chosen as IBS CI(Chief ..

    The Institute of Basic Science (IBS) selected three professors, Sang-il Eom, Homin Kim, and Meeyoung Cha, to explore new areas of basic science and conduct challenging independent research. The CI system supports independent research by the research manager of global research institutions. The research manager selected as CI forms an independent research group within the Pioneer Research Center (PRC). The PRC is a IBS research group and each group will receive between 10 and 1.5 billion won in research funds for five years. Among them, Meeyoung Cha, a professor of the School of Computing, will take charge of the Data Science Research Group. She is going to conduct a Data Science Study, which is necessary to analyze and solve the problems that appear in today’s network-connected information society. Based on human-social system modeling and analysis, Prof. Cha is focusing on calculating social science that has great potential for future society. “We will contribute to society by developing important future technologies, including detection of fake news based on big data and studying artificial intelligence that is comprehensible and fair,” Prof. Cha said. http://www.edaily.co.kr/news/read?newsId=01666246619434584&mediaCodeNo=257&OutLnkChk=Y

    ...Read more
  • KAIST Develops Next Generation Binary Analysis Pla..

    Over the past three years, Cha Sang-gil, a professor of School of Computing of KAIST, and his students have developed B2-R2, a technique for analyzing vulnerabilities in binary code using artificial intelligence technology with Cybersecurity Research Center(Director Professor Kim Yong-dae of Electrical and Electronic Engineering). B2-R2 is a performance system of 'Automatic Reverse Engineering and Vulnerability Detection-Based Technology Development' that is a research project by the Ministry of Science and ICT that can be used in various computer security areas such as ▲software security vulnerability analysis ▲Analysis of malicious code ▲Releasing obfuscation ▲Security Patch ▲Automatic Creation of Exposure plot. Compared to the binary analysis systems developed overseas, B2-R2 system is highly utilized (available on all operating systems such as Windows, Linux, Mac, Android, iOS) and has at least 2 to 100 times the analysis speed and maximizes the ease of analysis using the latest functional language, F#, and has a variety of interfaces with 32 programming languages. Not only is it the first binary code analysis system in Korea, but it also surpasses the BAP of Carnegie Mellon University and Angr of UCSB, which lead the field. The importance of binary analysis technology, known through ‘Next Generation binary analysis platform B2-R2 Technology Explanation Conference’ on Dec. 4, has become widely known through the Cyber Grand Challenge (CGC), the world's first computer-to-computer hacking attack and defense competition hosted by the Defense Department of Defense (DARPA) in 2016. With various security threats such as malicious code, APT attack, and DDoS attack being carried out by human hackers, the competition has become a signal for the emergence of AI-based machine hackers and can be understood as a core technology to prepare for a paradigm shift for information protection of the fourth industrial revolution. Professor Cha Sang-gil is known to be the main author who designed the core engine of the CGC championship, Mayhem, which was held in the U.S. and won the title by overwhelming margin at 2018 Information Security R&D Data Challenge Auto Detect based on AI, a Korean version of the CGC, on November 30. It is known that at the center of the system used for the contest by Cha Sang-gil B2-R2 technology which he developed with KAIST students for three years. According to information protection experts, KAIST's Cha Sang-gil team has secured key technologies in the field of 'automatic detection and response of AI-based vulnerabilities' that surpasses the world's highest level through this technical briefing and domestic competitions.

    ...Read more
  • Undergraduate Jae-min Hong of School of Computing,..

    At APLAS (Asian Symposium on Programming Language and Systems) 2018 which was held in Wellington, New Zealand on 12/3-5 and was sponsored by KAIST, Hong Jae-min (Advisor Ryu Seok-young) received the second prize for his thesis on Path Dependent Ties with Path-Equality at the Student Research Competition, which he participated with graduate students. He published the paper at ACM SIGPLAN Symposium on Scala, which was held in St. Louis, U.S. on September 28.

    ...Read more
  • Sung-ho Lee, Ph.D. student of KAIST School of Comp..

    LeeSeong-ho(Advisor Ryu Seok-young) School of Computing, KAIST was selected as the best reviewer for the Artifact Evaluation at OOPSLA 2018 (Object-Oriented Programming, Systems, Languages, and Applications), a class S international institute in Boston, U.S. on Nov. 7-9 and won the Distinguished Artifact Evaluation Committee Member Award.

    ...Read more
  • APLAS 2018 International Congress was chaired by P..

    The 16th APLAS (Asian Symposium on Programming Language and Systems), which KAIST supported as a Gold Sponsor, was held in Wellington, New Zealand, December 3, 2018. Professor Sukyoung Ryu, chair of the program, invited three world-renowned lecturers: Amal Ahmed (USA), Azalea Raad (MPI-SWS, Germany), and Bernard Scholes (University of Sydney, Australia), and conducted various programs including presentations of papers and poster sessions and workshops on December 2 and December 6, 2018.

    ...Read more
  • Chosen for NAVER Phd Fellowship

    Last November, ten Ph.D. students from our computer science department were chosen for NAVER PhD Fellowship. The selected person is - Gong Tae-sik (Professor: Lee Sung-joo) - Kwon Hyun (Professor Yoon Hyun-soo) - Kim Hyung-kyu (Professor Kim Soon-tae) - Nam Jae-hyun (Professor: Shin Seung-won) - Park Joon-young (Professor Ryu Seok-young) - Park Jin-seok (Professor Lee Heung-kyu) - Jang Young-soo (Professor: Kim Ki-ung) - Jeon Seok-joon (Professor: Kim Min-hyuk) - Jeong Dae-ryong (Professor: Shin In-shik) - Ha Jae-hee (Professor Kim Myung-chul) NAVER PhD Fellowship program is a program that selects Ph.D. student who submitted the first paper to the top-tier conference/journal of each computing field and pays scholarships. Naver selected eight students for NAVER Phd Fellowship in 2015, six first and eight second in 2016, 11 in 2017, and 10 in 2018, and paid a total of 235 million won to the selected students.

    ...Read more
  • Won K-ICT Cloud Industry Awards

    KAIST School of Computing won the K-ICT Cloud Industry Awards(Minister’s Award) at 2018 Grand Cloud Conference held at COEX in Seoul for building and operating a cloud that is currently being utilized. It was recognized as a good example of building a cloud operating system on idle equipment and providing computing for regular course and research tasks at the same time, and applying an operating system using open-source OpenStack. On the other hand, '2018 Grand Cloud Conference' is a Cloud Conference that summarizes the achievements of South Korea's Cloud industry and shares directions for future development. This is the place to discuss introducing and converging public and private clouds.

    ...Read more
  • Won Grand Prize at 2018 National Cryptographic Com..

    Two students from Graduate School of Information Security of School of Computing, KAIST, Choi Won-seok in Ph.d course and Lee Byeong-hak in master’s course(Advisor Professor Lee Ju-young) , won the grand prize for thesis “Indifferentiability of Truncated Random Permutations” at the 2018 National Cryptography Competition. The 2018 National Cryptographic Competition was held by the Korea Cryptographic Forum, Korea Institute of Information Security & Cryptology and and National Research Council of Science & Technology under the auspices of the National Intelligence Service to develop the nation's encryption technology. The total prize money is about 50 million won including the 10 million for the grand prize. Cryptographic Competition is divided into areas such as cryptography thesis, solving problems of cryptography, and ideas for using cryptography, and the grand prize is chosen only from the cryptography thesis area. The award ceremony was held at Ramada Seoul Hotel on November 15 as an additional event for the Future Password Workshop. In addition, Kim Sung-kwang in Ph.d course (Advisor Professor Lee Ju-young) received an incentive award in cryptography thesis section, and Kim Sung-kwang and Choi Won-suk in Ph.d course, and Lee Young-min in master’s course (Advisor Professor Lee Ju-young) received a special award.Two teams of undergraduates of KAIST hacking club GoN, led by Cha Sang-gil from Graduate School of Information Security, received the highest award and the incentive prize respectively in the problem-solving field. Meanwhile, Lee Ji-eun, a Ph.D. student in School of Computing, won the top prize at the National Cipher Skills Specialist Training Awards, and Lee Byeong-hak, a master's course student, won the excellence prize. Lee Byung-hak also won the top prize at the 2017 Cryptography Contest for his paper, "Tweakable Block Cippers Secure Beyond the Birtday Bound in the Ideal Cipher Model," which was adopted by the three major cryptographic societies Asiacrypt, this year.

    ...Read more
  • Professor Jinah Park delivered a keynote lecture a..

    Professor Jinah Park of the School of Computing at KAIST delievered a keynote lecture on the topic “Hippocampal Morphology Study based on Progressive Template Deformable Model” at the International Conference on Medical Imaging and Case Reports 2018 held in Baltimore in the U.S. from October 26 to 28, 2018. The event involved 70 people from 48 institutions in 23 countries. The event attracted many researchers who are influential in medical images and clinical studies including Dr. Marth Shenton from Harvard Medical School, Professor Polina Golland of MIT, Michael Miller and Professor Jeffery Siewerdwen of Johns Hopkins University.

    ...Read more
  • Top 15 Most Impactful Early Career Researchers in ..

    Professor Shin Yoo has been identified as one of the top 15 most impactful early career researchers in software engineering by a bibliographic study published in the Journal of Systems and Software in October 2018. The result is based on analysis of 14,456 papers as well as their citation counts published in top journals and conferences between 2010 and 2017. Prof. Yoo is an associate professor at the KAIST School of Computing. From 2012 to 2015, he was a lecturer of software engineering in the Centre for Research on Evolution, Search, and Testing (CREST) at the University College London, UK. Prof. Yoo received a Ph.D. in Computer Science from King’s College London, UK, in 2009. His main research interest is in Search Based Software Engineering (SBSE), specifically, the use of meta-heuristics and computational intelligence, such as genetic algorithm, to automatically solve various problems in software engineering, especially those related to testing and debugging.

    ...Read more
  • Professor Min H. Kim has chosen the best research ..

    Professor Min H. Kim has chosen the best research and development of 2018 top 100 Six professors from KAIST have been selected for the "Top 100 2018 state research and development" announced by the Ministry of Science and ICT and the Korea Institute for Science and Technology Planning. The winners are Il-du Kim and Byeong-gook Park at the Department of New Material Engineering, Ho-min Kim at the Graduate School of Medicine, Jae-woo Lee at the Department of Biochemistry, Min H. Kim at the School of Computing, and Kyung-chul ​ Choiat the Department of Electrical and Electronic Engineering. Professor Min H. Kim of the School of Computing was chosen for excellence in the field of information and electronics. It was recognized that he developed high-performance imaging technology to obtain high-performance images. Professor Il-du Kim was chosen as the best performance in the field of machinery and materials. It was recognized that he developed ultra-high sensitivity gas sensor platform material based on self-assembly organic complex catalyst coupling. Professor Byung-kook Park was also chosen for excellence in the machine and material fields. He has developed a material technology that obtains spin current from heat. Ho-min Kim , a professor at the medical school, was selected as the best performance in the life and ocean fields. It has established the 3rd structure and molecular warfare of core protein that controls the formation of synapses. Professor Jae-woo Lee has been chosen for excellence in energy and the environment. He was credited with developing high-value carbon-material synthesis technology. Kyung-chul Choi was chosen as the best performance in information and electronics. It was recognized that it developed a smooth display that was implemented on top of clothes. The performance selected for excellence will be awarded to the Minister of Science and ICT with a certificate and a signboard. The six selected professors will be nominated as candidates for the state-funded R&D achievement evaluation (medal, presidential citation, and the prime minister's citation) and will receive preferential treatment in the selection of new R&D projects.

    ...Read more
  • Top 100 R&D Achievement of 2018

    Professor Min H. Kim was selected for the “Top 100 Research and Development Projects of 2018” with five other professors at KAIST, announced by the Ministry of Science and ICT and the Korea Institute for Science and Technology Planning. His work was selected for excellence in the field of information and electronics. Prof. Kim and his team developed high-performance imaging technology to obtain high-performance images. The professors selected for excellence are awarded a certificate by the Minister of Science and ICT. The awardees were nominated as candidates through the state-funded R&D achievement evaluation and will receive preferential treatment in the selection of new R&D projects.

    ...Read more
  • KAIST School of Computing Professor Eun-Ho Yang a..

    "DropMax," "Adaptive Variable Softmax," "Uncertified-Aware Attachment," a joint study by Professor Yang Eun-Ho and Professor Hwang Seong-ju of the KAIST School of Computing, were published by Neural Information Processing System (NIPS) 2018 (acceptance rate:20.8 %), the world's best academic institution. The paper was published as follows: [DropMax: Adaptive Variational Softmax] In this paper, we propose techniques to improve the performance of the systeresis by applying Dropout techniques to softmax functions that are originally applied to multi-class identification. At each learning quarter, the whole class' subset is randomly sampled according to the learned Dropout probability and the discrimination is performed. There is meaning that is is a ensemble of different discriminations', and it also has the effect of making more comparisons between classes that are likely to be confused with each other. Deep Bayesian techniques enable the learning and reasoning of this probabilistic neural network. Specifically, it has been experimentally verified in this paper that inducing a Dropout mask, the probability of being a target label for each class, differently for each input instance and correctly deduplicating the values is important for improving performance, thereby enabling more reliable learning and reasoning. [Uncertainty-Aware Attention for Reliable Interpretation and Prediction] Existing in-depth neural networks cannot take into account uncertainty in the in-depth learning process of predictive models, so the learning model has the potential to predict the wrong situation, and the uncertainty present in the data and the model itself has led to false predictions. The "Uncertified-Aware Attachment for Reliable Interprevention and Prescription" paper is a way to overcome existing uncertainty problems. The "Uncertified-Aware Attachment for Reliable Interprevention and Prescription" paper is a way to overcome existing Uncertainty problems. Uncertainty-Aware Attachment Mechanism, which allows input-adaptive organic learning by identifying data and model conditions regarding uncertainty, was presented. This paper has experimentally demonstrated that, with respect to the performance of modern machine learning algorithms, the ability to interpret accurate models with corrected model predictive performance and uncertainty is outstanding through UA framework. [Joint Active Feature Acquisition and Classification with Variable-size Set Encoding] This paper addresses the question of learning policies to obtain effective information at a lower cost in situations where the cost of obtaining the necessary information in the classification (e.g., examination costs) is incurred, such as diagnosing diseases. When diagnosing patients, it is reasonable to perform the necessary tests according to the individual's condition rather than carrying out and diagnosing all the same types of tests. In this paper, it jointly learns about dynamic feature acquisition policies and classification models that determine the required information sequentially based on the information currently in place. To this end, we defined a function for the purpose of considering both the classification performance and the costs necessary to obtain information, and presented a joint learning framework for the feature acquisition policy and classification model using in-depth hardening learning. In addition, experiments using synthetic and medical data have shown that the performance is cost-effective compared to static feature acquisition methods or previous studies.

    ...Read more
  • Intelligent Service Integration (ISI) Laboratory o..

    Intelligent Service Integration (ISI) Laboratory of KAIST School of Computing(Prof. Han Dongsoo) has decided to carry out the international academic project for the development of Global Indoor Positioning System with Global H Company. Global H will support KAIST $ 400,000 for the project, which will be accompanied by technology transfer. The ISI Lab, which developed the KAIST Indoor Positioning System (KAILOS) in 2014 and released to the public, has recently developed a crowd sourcing AI technique that automatically labels the location of wireless signals acquired from unspecified number of smartphone users. In this joint international project, KAIST will upgrade location labeling AI technique using crowdsourcing to commercialization level. If the project is successfully performed, H Company is expected to install the system developed by KAIST its products and commercialize it. Professor Han Dongsoo, who will lead the international industry project with H company to be conducted over the next year, said, "It is a pity that the technology developed by KAIST will be commercialized through overseas companies before the domestic companies. The result is that domestic regulations on location services are too strict. " Professor Han Dongsoo said, "It is significant that a global company recognized the technology developed by KAIST and commissioned an industrial project for commercialization. Technology continues to decline and disappear if not developed. We will continue to expand international industry-academia cooperation in the field of indoor location recognition in the future. "

    ...Read more
  • Professor Kwang-Jo Kim, publication on network int..

    Kim Kwang, professor of KAIST (President: Sang Chul Shin) Graduate School of Computing and Information Security Graduate School, along with Muhamad Erza Aminanto and Dr. Harry Chandra Tanuwidjaja, Ph.D. students from Indonesia, wrote an English book called “Network Intrusion Detection using Deep Learning : A Feature Learning Approach” (in the aspected of network intrusion detection using features of deep learning) which supported by IITP’s project on “Communication Technology Research using Bio-inspired Algorithm” from April 2018 to February 2018. He has published this in one of the cyber security systems and networking series at Springer, a prominent publisher in Germany. This book introduces various methods of intrusion detection system using deep learning, which is artificial intelligence technique and widely used in computer vision, natural language processing, image processing, etc., and described an intrusion detection technique which extracts and learns the features of intrusion traffic with very high scan rate (99.918%) and low false positives (0.012%) compared to existing skills. Annexes include technical trends on artificial intelligence techniques for detecting malicious codes. This book will serve as a good guide for undergraduate and graduate students, R & D personnel in providing practical knowledge of establishing cyber security systems regarding graft artificial intelligence onto cyber security. 참조: https://www.springer.com/gp/book/9789811314438

    ...Read more
  • Professor Moonzoo Kim delivered a keynote speech a..

    Professor Moonzoo Kim delievered a keynote speech at the 15th International Conference on Formal Aspects of Component Software (FACS) which was held from October 10 to 12, 2018 with Professor Edward Lee of UC Berkeley and Professor Gigore Rosu of UIUC. His talk was titled “Lessons Learned from Automated Analysis of Industrial SW for 15 Years”.

    ...Read more
1 2 3 4 5 6 7 8