• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.245-250
• /
• 2023

RLHF(Reinforcement Learning from Human Feedback, 인간 피드백 기반 강화학습) 방법론이 최근 고성능 언어 모델에 많이 적용되고 있다. 이 방법은 보상 모델과 사람의 피드백을 활용하여 언어 모델로 하여금 사람이 선호할 가능성이 높은 응답을 생성하도록 한다. 하지만 상업용 언어 모델에 적용된 RLHF의 경우 구현 방법에 대하여 정확히 밝히고 있지 않다. 특히 강화학습에서 환경(environment)을 담당하는 보상 모델을 어떻게 설정하는지가 가장 중요하지만 그 부분에 대하여 오픈소스 모델들의 구현은 각각 다른 실정이다. 본 연구에서는 보상 모델을 훈련하는 큰 두 가지 갈래인 '순위 기반 훈련 방법'과 '분류 기반 훈련 방법'에 대하여 어떤 방법이 더 효율적인지 실험한다. 또한 실험 결과 분석을 근거로 효율성의 차이가 나는 이유에 대하여 추정한다.

• Journal of Labour Economics
• /
• v.24 no.3
• /
• pp.83-117
• /
• 2001

This study intends to analyze the status and efficiency of education-training in Korean firm. A study on the education-training in firm is very important nowadays, but the study level on this issue in Korea is low. The study method of this paper is the case study on a high-level Korean firm in the education-training status. This study first attempted to analyze the concept and size of the education-training in firm. And then this study figured out factors that determine the efficiency of education-training. Finally, I analyzed the status and efficiency of education-training in this case firm. Unfortunately, the efficiency level of my case firm in the education-training was low, in spite of a high-level firm in the education-training status. To upgrade the efficiency level of this firm in the education-training, this firm has to resolve many tasks.

• Journal of the Korea Safety Management & Science
• /
• v.12 no.4
• /
• pp.279-288
• /
• 2010

지식기반 경제 사회의 진입과 더불어 조직에서 가장 중요한 요소는 인적자원이며 인적자원의 효율적인 활용이야말로 기업 경영에 있어서 핵심이라고 할 수 있다. 이러한 인적자원의 역량을 향상시킬 수 있는 방법으로 대부분의 기업들은 교육훈련을 실시하고 있다. 교육훈련의 효율적인 활용이야말로 인적자원의 개발이고, 인적자원의 개발이 기업의 지속가능한 경영에 가장 중요한 부분이라고 할 수 있다. 인적자원 개발을 위한 교육훈련이 조직의 발전에 최우선이 되어야 함은 아무리 강조해도 지나침이 없다. 기업에 있어서 사람이 자산인데 자산을 키우기 위한 최선의 방법으로도 기업들은 효율적인 교육 훈련에 많은 연구를 실시하고 있다. 인적자원이 기업의 성패를 좌우할 만큼 중요한 핵심요소이고 기업의 핵심인 인적자원을 개발하기 위해선 교육 훈련이 핵심이고 핵심인 교육훈련은 기업의 인적자원개발에 대부분을 차지하고 있다고 해도 과언이 아닐 것이다. 따라서 본 연구의 목적은 기업교육의 효율성을 제고하기 위하여 HRD 요소들에 있어서 조직원 직무향상을 위한 교육효과에 초점을 맞추었다. 교육훈련에 관한 요인분석 결과 교육의 중요성인지, 교육 참가횟수, 교육내용 등의 사전인지가 교육의 효과를 높이는 요인으로 나와 있고, 이러한 결과를 토대로 회귀모형 분석을 제시하였다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2018.11a
• /
• pp.25-26
• /
• 2018

Virtual training is widely used based on safety and cost efficiency as a way to efficiently train based on virtual reality. In this paper, we propose the implementation and validation evaluation of life safety training, life training in closed area training, initial fire extinguishing training as a virtual training in maritime safety training. Specifically, we discuss how to implement virtual training to meet the goals of each training, and we propose training methods for evaluating trainees' effectiveness when implemented in this manner. The proposed evaluation method can be used as a quantitative evaluation index of the trainee's training assessment of the training and the safety contribution of the training to the evaluation of the training efficienc

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.10
• /
• pp.1816-1823
• /
• 1992

In order to develop general CMAC training technique applicable to any CMAC, characteristics of CMAC learning algorithm and training problems of CMAC are studied. Neighborhood Sequential Training technique which is general and free fro CMAC learning interference is proposed. The technique is used to generate mathematical functions and found to be effective.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2015.11a
• /
• pp.89-91
• /
• 2015

사회의 발전과 더불어 현시대에는 지역적으로 특성화된 재난의 급증과 함께, 각종 재난 유형의 복합화와 대형화가 일어나고 있는 실정이다. 이에 반하여 현재 적용되고 있는 재난대응 훈련의 조치들은 증가하는 재난의 위험에 발맞추지 못한 채 한계에 부딪쳐 답보중인 상태이다. 이에 따라 재난대응역량 강화를 위하여 현장의 긴박한 상황을 이해하여 빠른 상황판단을 할 수 있는, 현실감 있고 생동감 있는 훈련 시뮬레이터의 개발이 추진되고 있다. 더불어, 훈련 시뮬레이터의 개발뿐 아니라 시뮬레이터의 효율적인 이용과 변화하고 있는 현대 재난에 대한 발 빠른 대응을 위하여, 기존의 단편, 부분적인 훈련 시스템을 탈피한 새로운 훈련 시뮬레이터에 대응하는 훈련 방안과 재난대응훈련 평가체계 방법에 관한 연구도 필요한 실정이다. 본 논문에서는 개발되고 있는 증강현실기반 시뮬레이터를 활용한 재난대응 훈련 방안 개발 내용을 소개하며 연구의 목표와 기대성과에 대해서 설명하고자 한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.5A
• /
• pp.479-486
• /
• 2008

In this paper, an efficient training symbol design with m-sequence is proposed for the MIMO-OFDM based next generation wireless transmission system which supports gigabits per second data rate. In the traditional blute force method, the preamble design is based on the case by case comparison with the system requirements. This paper discusses a training symbol design methodology for the MIMO-OFDM system based on the m-sequence which has been widely used in the spread spectrum communication areas due to its good correlation characteristics. Also the step-by-step design and performance verification method within the limited search space is discussed. The proposed method targets the design of the training symbol which satisfies system requirements for the packet based MIMO-OFDM wireless communication system including automatic gain control(AGC), timing synchronization, frequency and sampling offset estimation, and MIMO channel estimation.

• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.487-494
• /
• 2022

Purpose: This study proposes a Metaverse-based police education and training model that can efficiently improve the performance of various police activities according to changes in the environment of the times. Method: The structure of this system can generate Avatar Controller expressed using HMD and haptic technology, access the Network Interface, and educate and train individually or on a team basis through the command control module, education and training content module, and analysis module. Result: In the proposed model of this study, the command and control module was incorporated into individual or team-based education and training, enabling organic collaborative training among team members by monitoring the overall situation of terrorism or crime in real time. Conclusion: Metaverses-based individual or team-based police education and training can provide a more efficient and safe education and training environment based on immersion, interaction, and rapid judgment in various situations.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.369-377
• /
• 2010

In vocabulary recognition systems based on HMM(Hidden Markov Model)s, training process unseen model bring on show a low recognition rate. If recognition vocabulary modify and make an addition then recreated modeling of executed database collected and training sequence on account of bring on additional expenses and take more time. This study suggest efficient context dependent process modeling method using decision tree-based state tying. On study suggest method is reduce recreated of model and it's offered that robustness and accuracy of context dependent acoustic modeling. Also reduce amount of model and offered training process unseen model as concerns context dependent a likely phoneme model has been used unseen model solve the matter. System performance as a result of represent vocabulary dependence recognition rate of 98.01%, vocabulary independence recognition rate of 97.38%.

• The Journal of the Korea Contents Association
• /
• v.13 no.11
• /
• pp.106-118
• /
• 2013

I discussed how the Zen training could be used to previous acting training methods focused on the way draw efficiently subconsciousness in the process of the training of actors. It is believed that the practice of the Zen would contribute to the development of training subconsciousness of actors. I examined the validities of the Zen practices which could be helpful to young students and existing actors' training processes and started from the existing proven analyses of mental and psychological effects of it. It is certain that the practices of Zen is a new continent which has infinite possibilities of analyzing and studying in terms of thinking highly of the Zen and brain science together. If we would utilize the Zen efficiently in the course of training actors, we could achieve four elements: the first, a trigger to operate actors' subconsciousness, the second, establishing the presence of actors through the reinforcement of concentration, the third, overcoming any mental and psychological obstacles, and the fourth, the establishment of transformation skills through the combined use of left and right brains. Additionally, actors could have mental and psychological stability through the Zen practice in their daily lives. I believe that we could also find a unique Eastern actor training way through vigorous and practical following analyses and practices which are based on the Zen tradition for training actors' subconsciousness and unconsciousness.