• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Journal of The Korean Association For Science Education
• /
• v.38 no.5
• /
• pp.599-610
• /
• 2018

The purpose of this study is to analyze mechanistic reasoning in Fabre's inquires and to develop mechanistic reasoning model. To analyze the order of the process elements in mechanistic reasoning, 30 chapters were selected in book. Inquiries were analyzed through a framework which is based on Russ et al. (2008). The nine process elements of mechanistic reasoning that was presented in Fabre's inquires were as follows: Describing the Target Phenomenon, Identifying prior Knowledge, Identifying Properties of Objects, Identifying Setup Conditions, Identifying Activities, Conjecturing Entities, Identifying Properties of Entities, Identifying Entities, and Organization of Entities. The order of process elements of mechanistic reasoning was affected by inquiry's subject, types of question, prior knowledge and situation. Three mechanistic reasoning models based on the process elements of mechanistic reasoning were developed: Mechanistic reasoning model for Identifying Entities(MIE), Mechanistic reasoning model for Identifying Activities(MIA), and Mechanistic reasoning model for Identifying Properties of entities (MIP). Science teacher can help students to use the questions of not only "why" but also "How", "If", "What", when students identify entities or generate hypotheses. Also science teacher should be required to understand mechanistic reasoning to give students opportunities to generate diverse hypotheses. If students can't conjecture entities easily, MIA and MIP would be helpful for students.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.984-987
• /
• 2020

최근 오픈 도메인 자연어 질문 응답 분야에서는 폭넓은 다중 문서들을 토대로 다중 홉 추론과 동시에 서로 다른 수준의 여러 문제들을 한꺼번에 해결해야 하는 다중 작업 질문 응답에 관한 관심이 높다. 본 논문에서는 이러한 다중 홉 추론과 다중 작업을 요구하는 복잡 질문들에 효과적으로 응답하기 위해, 계층적 그래프 기반의 새로운 심층 신경망 모델을 제안한다. 제안 모델에서는 계층적 그래프와 그래프 신경망을 이용해 다중 문서들로부터 서로 다른 수준의 맥락 정보를 얻어낸 후, 이들을 활용하여 뒷받침 문장들, 답변 영역, 응답 유형 등을 동시에 구해야 하는 다중 작업 문제에 관한 답들을 예측해낸다. 본 논문에서는 오픈 도메인 자연어 질문 응답 데이터 집합인 HotpotQA를 이용한 실험들을 통해, 제안 모델의 긍정적 효과를 입증한다.

• Journal of Elementary Mathematics Education in Korea
• /
• v.20 no.4
• /
• pp.655-676
• /
• 2016

The purpose of this study is to examine the effects of teaching on functional thinking, one of the algebraic thinking in sixth grade students level. For this study, we developed functional thinking based-teaching through analyzing mathematical curriculum and preceding research, which consisted of 12 classes, and we investigated the effects of teaching through quantitative and qualitative analysis. In the results of this study, functional thinking based-teaching was statistically proven to be more effective in improving algebraic reasoning skills and lower elements which is an algebraic reasoning as generalized arithmetic and functional thinking, compared to traditional textbook-centered lessons. In addition, the functional thinking based-teaching gave a positive impact on the functional thinking level. Thus functional thinking based-teaching provides guidance on the implications for teaching and learning methods and study of the functional thinking in the future, because of the significant impact on the mathematics learning in six grade students.

• The KIPS Transactions:PartD
• /
• v.11D no.5
• /
• pp.1189-1196
• /
• 2004

It is a major concern of e-shopping mall managers to satisfy a variety of customer's desire by recommending a proper product to the perspective purchaser. Customer information like customer's fondness, age, gender, etc. in shopping has not been used effectively for the customers or the suppliers. Conventionally, e-shopping mall managers have recommended specific items of products to their customers without considering thoroughly in a customer point of view. This study introduces the ways of a choosing and recommending of products using case-based reasoning and rule-based reasoning for customer themselves or others. A similarity measure between one member's idiosyncrasy and the other members' is developed based on the rule base and the case base. The case base is improved for the system intelligence by recognizing and learning the changes of customer's desire and shopping trend.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.287-308
• /
• 2023

After launching its service in November 2022, ChatGPT has rapidly increased the number of users and is having a significant impact on all aspects of society, bringing a major turning point in the history of artificial intelligence. In particular, the inference ability of large language models such as ChatGPT is improving at a rapid pace through prompt engineering techniques. This reasoning ability can be considered as an important factor for companies that want to adopt artificial intelligence into their workflows or for individuals looking to utilize it. In this paper, we begin with an understanding of in-context learning that enables inference in large language models, explain the concept of prompt engineering, inference with in-context learning, and benchmark data. Moreover, we investigate the prompt engineering techniques that have rapidly improved the inference performance of large language models, and the relationship between the techniques.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.309-328
• /
• 2022

This study empirically analyzed a Korean pre-trained language models (PLMs) designed for natural language generation. The performance of two PLMs - BART and GPT - at the task of abstractive text summarization was compared. To investigate how performance depends on the characteristics of the inference data, ten different document types, containing six types of informational content and creation content, were considered. It was found that BART (which can both generate and understand natural language) performed better than GPT (which can only generate). Upon more detailed examination of the effect of inference data characteristics, the performance of GPT was found to be proportional to the length of the input text. However, even for the longest documents (with optimal GPT performance), BART still out-performed GPT, suggesting that the greatest influence on downstream performance is not the size of the training data or PLMs parameters but the structural suitability of the PLMs for the applied downstream task. The performance of different PLMs was also compared through analyzing parts of speech (POS) shares. BART's performance was inversely related to the proportion of prefixes, adjectives, adverbs and verbs but positively related to that of nouns. This result emphasizes the importance of taking the inference data's characteristics into account when fine-tuning a PLMs for its intended downstream task.

• Korean Journal of Logic
• /
• v.14 no.2
• /
• pp.39-76
• /
• 2011

We explain some basic elements of Martin-L$\ddot{o}$f's type theory and examine the distinction between propositions and judgments. In section 1, we introduce the problem. In section 2, we explain the concept of proposition in the intuitionistic type theory as a development of the intuitionistic conception of proposition. In section 3, we explain the concept of judgment in the intuitionistic type theory. In section 4, we explain some basic inference rules and examine a particular derivation in the theory. In section 5, we examine one route from the Fregean distinction between propositions and judgments to the distinction between them in the intuitionistic type theory, paying attention to the alleged necessity for introducing different forms of judgments.

• 대한방사선방어학회:학술대회논문집
• /
• 2009.04a
• /
• pp.140-141
• /
• 2009

See Full Text

• 대한방사선방어학회:학술대회논문집
• /
• 2009.04a
• /
• pp.264-265
• /
• 2009