人工知能学会論文誌
Online ISSN : 1346-8030
Print ISSN : 1346-0714
ISSN-L : 1346-0714
38 巻, 2 号
選択された号の論文の5件中1~5を表示しています
一般論文
原著論文
  • 張 鑫, 松嶋 達也, 松尾 豊, 岩澤 有祐
    原稿種別: 原著論文(技術)
    2023 年 38 巻 2 号 p. A-LB3_1-10
    発行日: 2023/03/01
    公開日: 2023/03/01
    ジャーナル フリー

    Imitation Learning (IL) is anticipated to achieve intelligent robots since it allows the user to teach the various robot tasks easily.In particular, Few-Shot Imitation Learning (FSIL) aims to infer and adapt fast to unseen tasks with a small amount of data. Though FSIL requires few-shot of data, the high cost of demonstrations in IL is still a critical problem. Especially when we want to teach the robot a new task, we need to execute the task for the assignment every time. Inspired by the fact that humans specify tasks using language instructions without executing them, we propose a multi-modal FSIL setting in this work. The model leverages image and language information in the training phase and utilizes both image and language or only language information in the testing phase. We also propose a Multi-Modal Meta-Imitation Learning or M3IL, which can infer with only image or language information. The result of M3IL outperforms the baseline in the standard and proposed settings. Our result shows the effectiveness of M3IL and the importance of language instructions in the FSIL setting.

  • 関根 由可里, 中島 敬祐, 大竹 景子, 瀧沢 岳, 杉山 淳一, 向井 大誠, 柿澤 恭史, 倉橋 節也
    原稿種別: 原著論文(技術)
    2023 年 38 巻 2 号 p. B-MA6_1-11
    発行日: 2023/03/01
    公開日: 2023/03/01
    ジャーナル フリー

    With the spread of COVID-19, the risk of droplet infection has been studied through interdisciplinary research. However, there is little information on the spread of the pathogen through human contact behavior. In this paper, we focus on the home, which is the private space of people, and propose a model to visualize the risk of contact infection to a family when people return home by combining calculation of contact behavior after returning home and study of virus transfer efficiency. First, from the contact behavior data for the first 30 minutes after returning home, we calculated the probability of flow line, the distribution of the number of contacts, the probability of initial action and the probability of contact behavior transmission. Next, we obtained the transfer efficiency between the substrate representing the household goods surface and the model skin, and the rate of change of the viral transfer efficiency when people continuously contact the household goods surface. According to these probabilities, we reproduced the state in which the virus attached to the hand or household goods surface by probabilistically performing the agent’s movement and contact behavior after returning home. This result shows that when agents return home with viruses attached to their hands, the viruses are widely confirmed on household goods surfaces. Furthermore, by simulating the combination and timing of hygienic actions such as handwashing and disinfection, it was possible to visualize their effects on the risk of re-contact and care effects.

速報論文
原著論文
  • 兼岩 憲, 山中 佑紀
    原稿種別: 原著論文(技術)
    2023 年 38 巻 2 号 p. D-M53_1-9
    発行日: 2023/03/01
    公開日: 2023/03/01
    ジャーナル フリー

    In the Semantic Web, items are represented by uniform resource identifiers (URIs) on the Web in order to describe relationships between things in resource description framework (RDF) graphs. Large scale open RDF data (linked data) describing information about various things are available. Hence, relational discovery research has been conducted using RDF data to explore relationships between things. The SPARQL protocol and RDF query language (SPARQL) is usually employed to process RDF data; however, SPARQL is not suitable for relational discovery using linked data because it is difficult to describe unknown vocabularies and relationships in SPARQL queries. In this paper, we propose an aggregation path search for RDF graphs as an extension of shortest path keyword search. The aggregation path search is devised to find RDF paths by merging multiple resource URIs into commonly reachable nodes in an RDF graph. This search method can discover new relationships between items that are connected by a common node. We present a method for treating equivalent resource URIs as a single resource URI; these equivalent URIs essentially represent the same thing based on equivalence relations in different RDF datasets. In our experiments, we show in the integration of multiple large scale RDF datasets that the integration of equivalent resources enables richer retrieval of aggregated paths.

  • 野田 恭平, 高橋 久尚, 津田 宏治 , 廣島 雅人
    原稿種別: 原著論文(技術)
    2023 年 38 巻 2 号 p. E-M93_1-11
    発行日: 2023/03/01
    公開日: 2023/03/01
    ジャーナル フリー

    Due to the increase in material databases in recent years, there has been a lot of research regarding deep learning models which use large sizes of datasets and are aimed at the prediction of the material properties of inorganic compounds. Particularly, prediction models with Self-Attention structures, such as Roost and CrabNet, have garnered attention because of two reasons: (1) input variables are confined to the chemical composition of each formula and (2) Self-Attention enables models to learn individual element representations based on their chemical environment. However, the existing Self- Attention model yields low prediction accuracy when predicting structure-dependent material properties, such as the magnetic moment, for lack of structural information of compounds as input. In this research, based on the existing Self- Attention model, we set both elemental and structural information, especially the space group number and lattice constant, as input information and successfully construct a prediction model that is more versatile than existing methods. Furthermore, we visualized lists of promising materials by adopting Bayesian optimization. As a result, we have developed a system to propose desired materials for materials researchers.

feedback
Top