• 전자통신동향분석
• /
• 제35권3호
• /
• pp.66-75
• /
• 2020

As the increasing expectations of a practical AI (Artificial Intelligence) service makes AI algorithms more complicated, an efficient processor to process AI algorithms is required. To meet this requirement, processors optimized for parallel processing, such as GPUs (Graphics Processing Units), have been widely employed. However, the GPU has a generalized structure for various applications, so it is not optimized for the AI algorithm. Therefore, research on the development of AI processors optimized for AI algorithm processing has been actively conducted. This paper briefly introduces an AI processor especially for inference acceleration, developed by the Electronics and Telecommunications Research Institute, South Korea., and other global vendors for mobile and server platforms. However, the GPU has a generalized structure for various applications, so it is not optimized for the AI algorithm. Therefore, research on the development of AI processors optimized for AI algorithm processing has been actively conducted.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권3호
• /
• pp.170-177
• /
• 2010

Poker is a game of imperfect information where competing players must deal with multiple risk factors stemming from unknown information while making the best decision to win, and this makes it an interesting test-bed for artificial intelligence research. This paper introduces a new learning AI algorithm with embedded opponent modeling that can be used for these types of situations and we use this AI and apply it to a poker program. The new AI will be based on several graphs with each of its nodes representing inputs, and the algorithm will learn the optimal decision to make by updating the weight of the edges connecting these nodes and returning a probability for each action the graphs represent.

• Nuclear Engineering and Technology
• /
• 제56권6호
• /
• pp.1989-2001
• /
• 2024

Artificial intelligence (AI) techniques are now being considered in the nuclear field, but application faces with the lack of actual plant data. For this reason, most previous studies on AI applications in nuclear power plants (NPPs) have relied on simulators or thermal-hydraulic codes to mimic the plants. However, it remains uncertain whether an AI model trained using a simulator can properly work in an actual NPP. To address this issue, this study suggests the use of metadata, which can give information about parameter trends. Referred to here as robust AI, this concept started with the idea that although the absolute value of a plant parameter differs between a simulator and actual NPP, the parameter trend is identical under the same scenario. Based on the proposed robust AI, this study designs an event diagnosis algorithm to classify abnormal and emergency scenarios in NPPs using prototypical learning. The algorithm was trained using a simulator referencing a Westinghouse 990 MWe reactor and then tested in different environments in Advanced Power Reactor 1400 MWe simulators. The algorithm demonstrated robustness with 100 % diagnostic accuracy (117 out of 117 scenarios). This indicates the potential of the robust AI-based algorithm to be used in actual plants.

• 한국의류학회지
• /
• 제45권5호
• /
• pp.892-906
• /
• 2021

This study explores the effects of providing information on the price fairness perception and intention of continuous use in an online fashion platform, given a price difference due to AI algorithm pricing. We investigated the moderating roles of price inequality (loss vs. gain) and technology insecurity. The experiments used four stimuli based on price inequality (loss vs. gain) and information provision (provided or not) on price inequality. We developed a mock website and offered a scenario on the product presentation based on an AI algorithm pricing. Participants in their 20s and 30s were randomly allocated to one of the stimuli. To test the hypotheses, a total of 257 responses were analyzed using Process Macro 3.4. According to the results, price fairness perception mediated between information provision and continuous use intention when consumers saw the price inequality as a gain. When the consumers perceived high technology insecurity, information provision affected the intention of continuous use mediated by price fairness perception.

• 드라이브 ㆍ 컨트롤
• /
• 제18권1호
• /
• pp.24-30
• /
• 2021

There is an increasing interest in condition-based maintenance for the prevention of economic loss due to failure. Moreover, immense research is being carried out in related technologies in the field of construction machinery. In particular, data-based failure diagnosis methods that employ AI (machine & deep learning) algorithms are in the spotlight. In this study, we have focused on the failure diagnosis and mode classification of reduction gear of excavator's travel device by using the AI algorithm. In addition, a remote monitoring system has been developed that can monitor the status of the reduction gear by using the developed diagnosis algorithm. The failure diagnosis algorithm was performed in the process of data acquisition of normal and abnormal under various operating conditions, data processing and analysis by the wavelet transformation, and learning. The developed algorithm was verified based on three-evaluation conditions. Finally, we have built a system that can check the status of the reduction gear of travel devices on the web using the Edge platform, which is embedded with the failure diagnosis algorithm and cloud.

• 전자통신동향분석
• /
• 제37권1호
• /
• pp.53-62
• /
• 2022

With increasing size of transformer-based neural networks, a light-weight algorithm and efficient AI accelerator has been developed to train these huge networks in practical design time. In this article, we present a survey of state-of-the-art research on the low-precision computational algorithms especially for floating-point formats and their hardware accelerator. We describe the trends by focusing on the work of two leading research groups-IBM and Seoul National University-which have deep knowledge in both AI algorithm and hardware architecture. For the low-precision algorithm, we summarize two efficient floating-point formats (hybrid FP8 and radix-4 FP4) with accuracy-preserving algorithms for training on the main research stream. Moreover, we describe the AI processor architecture supporting the low-bit mixed precision computing unit including the integer engine.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.190-201
• /
• 2023

Securing transportation safety infrastructure technology for Lv.4 connected autonomous driving is very important for the spread of autonomous vehicles, and the safe operation of level 4 autonomous vehicles in adverse weather has limitations due to the development of vehicle-only technology. We developed the radar-enabled AI convergence transportation entities detection system. This system is mounted on fixed and mobile supports on the road, and provides excellent autonomous driving situation recognition/determination results by converging transportation entities information collected from various monitoring sensors such as 60GHz radar and EO/IR based on artificial intelligence. By installing such a radar-enabled AI convergence transportation entities detection system on an autonomous road, it is possible to increase driving efficiency and ensure safety in adverse weather. To secure competitive technologies in the global market, the development of four key technologies such as ① AI-enabled transportation situation recognition/determination algorithm, ② 60GHz radar development technology, ③ multi-sensor data convergence technology, and ④ AI data framework technology is required.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.693-696
• /
• 2021

강화학습에는 다양한 알고리즘이 있으며 분야에 따라 사용되는 알고리즘이 다르다. 게임 분야에서도 강화학습을 사용하여 인공지능을 개발할 때 특정 알고리즘이 사용된다. 알고리즘에 따라 학습 방식이 다르고 그로 인해 만들어지는 인공지능도 달라진다. 그러므로 개발자는 목적에 맞는 인공지능을 구현하기 위해 적절한 알고리즘을 선택해야 한다. 그러기 위해서 개발자는 알고리즘의 학습 방식과 어떤 종류의 인공지능 구현에 적용되는 것이 효율적인지 알고 있어야 한다. 따라서 이 논문에서는 게임 인공지능 구현에 사용되는 알고리즘인 SAC, PPO, POCA 세 가지 알고리즘의 학습 방식과 어떤 종류의 인공지능 구현에 적용되는 것이 효율적인지 비교한다.

• 한국통신학회논문지
• /
• 제35권12A호
• /
• pp.1181-1187
• /
• 2010

본 논문은 게임에서 신경망기반으로 지능캐릭터에게 학습을 통한 상황판단을 하는 이동 인공지능을 제안하였다. 신경망은 게임 규칙과 문제해결 방법을 정의한 알고리즘을 통한 입출력 값을 이용하여 지도 학습된다. 지도 학습된 지능캐릭터는 변화하는 주변 환경을 인지하여, 적절한 행동을 하게 된다. 본 논문에서는 신경망을 이용한 이동 인공지능을 점진적으로 설계하였고, 성능 실험을 위하여 간단한 게임을 구현하였다. 이 게임은 일정한 2차원 공간에 목표, 캐릭터, 장애물이 존재하고 캐릭터는 목표 지점으로 장애물을 회피하며 이동해야한다. 이동 인공지능은 실험마다 정의한 알고리즘을 통해 규칙과 몇 가지 문제해결법을 학습하여 변화하는 환경에서 목표를 완수 할 수 있으며, 정의한 알고리즘과 신경망 구조를 동일하게 설계하였다. 실험 결과, 제안한 이동 인공지능은 주변 상황을 인지하여 이동을 수행하고 목표를 완수할 수 있음을 보였다. 이동 인공지능은 복잡한 구조의 게임도 학습 알고리즘을 정의하여 학습하면 신경망은 변화한 환경에서도 적절한 결과를 보여 줄 수 있을 것이다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제25권4호
• /
• pp.23-36
• /
• 2016

Purpose Recently, many researchers have paid much attention to the Artificial Intelligence fields of GVGP, PCG. The paper suggests that the improved MCTS algorithm to apply for the framework can generate better AI agent. Design/methodology/approach As noted, the MCTS generate magnificent performance without an advanced training and in turn, fit applying to the field of GVGP which does not need prior knowledge. The improved and modified MCTS shows that the survival rate is increased interestingly and the search can be done in a significant way. The study was done with 2 different sets. Findings The results showed that the 10 training set which was not given any prior knowledge and the other training set which played a role as validation set generated better performance than the existed MCTS algorithm. Besed upon the results, the further study was suggested.