Search Results 1-20 of 129

  • Scheduling Computation Graphs of Deep Learning Frameworks for Multi-core CPUs  [in Japanese]

    樋口 兼一 , 田浦 健次朗

    Chainerを始めとする多くの深層学習フレームワークは,ニューラルネットワークに含まれる層ごとの処理をノード,各層間の接続関係をエッジとした計算グラフを内部的に構築し,各ノードを逐次に実行することによりネットワークの学習を行う.そのようなフレームワークにおけるホットスポットは各ノード内部の処理であり,既存の研究・実装はノード単位の高速化に焦点を当ててきた.しかし,広く用いられているネットワークモ …

    情報処理学会論文誌プログラミング(PRO) 13(1), 20-20, 2020-01-29

    IPSJ 

  • Detectability Limit of Graph Partitioning  [in Japanese]

    Kawamoto Tatsuro

    <p>グラフ分割,と言ってもあまり馴染みがないかもしれない.グラフ分割は,基本的には計算機科学・統計科学の対象であり,自然科学とは毛色が異なる面も存在するが,統計力学的なアプローチでの研究が近年も活発に進められている.</p><p>グラフ分割は,頂点と枝で構成されるグラフ(ネットワーク)から,いくつかの部分グラフに分割し,マクロなグループ構造を抽出する問題である …

    Butsuri 75(11), 696-700, 2020

    J-STAGE 

  • Learning mesh-based numerical analysis using graph neural networks  [in Japanese]

    HORIE Masanobu , MORITA Naoki , IHARA Yu , MITSUME Naoto

    … <p>メッシュは有限要素法や有限体積法で用いられる重要なデータ構造である.メッシュデータ構造はグラフと呼ばれるデータ構造の一種であるとみなせるため,メッシュを学習するために graph neural network (GNN) が広く用いられてきた.本研究では,GNN が有限要素解析の学習に有用なモデルであることを示す.提案手法では,メッシュの回転や並進に対して不変となるような形状の特徴量を入力として用いることによ …

    Transactions of the Japan Society for Computational Engineering and Science 2020(1), 20201005-20201005, 2020

    J-STAGE 

  • R-GCN Based Function Inference for Gate-level Netlist

    Amagasaki Motoki , Oyama Hiroki , Fujishiro Yuichiro , Iida Masahiro , Yasuda Hiroaki , Ito Hiroto

    … <p>Graph neural networks are a type of deep-learning model for classification of graph domains. … To infer arithmetic functions in a netlist, we applied relational graph convolutional networks (R-GCN), which can directly treat relations between nodes and edges. … In this paper, by considering the distribution of labels for each node, we show a R-GCN based function inference method and data augmentation technique for netlist having multiple functions. …

    IPSJ Transactions on System LSI Design Methodology 13(0), 69-71, 2020

    J-STAGE 

  • Concept Constructing in the Description Logic SROIQ based on Minimal RDF Reasoning  [in Japanese]

    Kaneiwa Ken , Nagai Takuma

    … <p>In the area of the Semantic Web, the expressive description logic SROIQ corresponding to OWL2 provides us rich reasoning and learning tasks for ontologies, e.g., inference engine, query-answering system, and concept learning. … In this paper, we propose (i) minimal model reasoning in the description logic SROIQ for RDF graphs and (ii) a SROIQ-concept constructing algorithm for the classes, properties and individuals in each RDF graph. …

    Transactions of the Japanese Society for Artificial Intelligence 35(1), B-J62_1-13, 2020

    J-STAGE 

  • Analytical Sociology and Causal Inference  [in Japanese]

    Takikawa Hiroki

    <p> 分析社会学はヨーロッパを中心に普及しつつある有望な社会学研究プログラムであり,その成否の検討は,社会学的研究一般の将来にとっても重要な意味をもつ.本研究は,なかでもその理論構想の基礎にある因果メカニズムの解明という考えに焦点をあて,その因果概念をめぐって,統計的因果推論との関係において検討を進める.具体的には,分析社会学の提唱するメカニズムによる因果説明と統計的因果推論との関係 …

    Sociological Theory and Methods 34(1), 47-64, 2019

    J-STAGE 

  • Investigation of Science Teaching Techniques which Make Use of Students' Mathematical Ability to Solve Analogical Problems: In Order to Have Students Comprehend the Meaning of a Graph  [in Japanese]

    ISHII Toshiyuki , OTOSHI Manami

    … of the science problem "A graph that is proportional first and then becomes constant after certain amounts are added." would be promoted by having them solve similar mathematics problems before working on the science problems.</p><p>The results show that students achieved higher marks in science tests by taking prior mathematics tests.</p><p>Teachers administered the students some easy mathematics problems similar to the science ones, which helped them build inference schema, and lead them to an …

    Journal of Science Education in Japan 43(3), 244-252, 2019

    J-STAGE 

  • <b>Study of "Structure Graph" Proposed by Professor Hideo Kasai: </b><b>Summary and Evolution </b>  [in Japanese]

    SHIONO Kiyoji

    <p>河西秀夫教授(故人)は露頭で観察した地質体の接触関係を「構造グラフ」,新旧関係を「層序グラフ」で表現する方法を提案した.構造グラフは地質体(頂点)の集合と隣接する地質体の順序対(辺)の集合および辺にラベル(接触関係の種類)を与える写像で定義されるラベル付き有向グラフである.層序グラフは構造グラフから導かれる新旧関係を表現するラベル付き有向グラフである.2つのグラフは露頭での観察結 …

    Geoinformatics 29(3), 95-110, 2018

    J-STAGE 

  • Detecting Architectural Violations Using Responsibility and Dependency Constraints of Components

    HAYASHI Shinpei , MINAMI Fumiki , SAEKI Motoshi

    … For this technique, the dependence graph among code fragments extracted from the source code and the inference rules according to the architecture are the inputs. … A set of candidate components to which a code fragment can be affiliated is attached to each node of the graph and is updated step-by-step. … The inference rules express the components' …

    IEICE Transactions on Information and Systems E101.D(7), 1780-1789, 2018

    J-STAGE 

  • Polynomial Time Learnability of Graph Pattern Languages Defined by Cographs

    SHOUDAI Takayoshi , YOSHIMURA Yuta , SUZUKI Yusuke , UCHIDA Tomoyuki , MIYAHARA Tetsuhiro

    … <p>A cograph (complement reducible graph) is a graph which can be generated by disjoint union and complement operations on graphs, starting with a single vertex graph. … With the goal of developing an effective data mining method for graph structured data, in this paper we introduce a graph pattern expression, called a <i>cograph pattern</i>, which is a special type of cograph having structured variables. …

    IEICE Transactions on Information and Systems E101.D(3), 582-592, 2018

    J-STAGE 

  • Growth Analysis Using Nuisance Baseline

    Kamo Ken-ichi , Tonda Tetsuji , Satoh Kenichi

    … After estimating the main parameters, we can graph the baseline trend, non-parametrically. … This implies that the estimate is stable in our model that is one of the advantage for statistical inference aspect.</p> …

    FORMATH 16(0), 12-21, 2017

    J-STAGE 

  • Low-Rank Representation with Graph Constraints for Robust Visual Tracking

    LIU Jieyan , MA Ao , LI Jingjing , LU Ke

    … In this paper, we propose a novel subspace representation algorithm for robust visual tracking by using low-rank representation with graph constraints (LRGC). … Low-rank representation has been well-known for its superiority of handling corrupted samples, and graph constraint is flexible to characterize sample relationship. … In this paper, we aim to exploit benefits from both low-rank representation and graph constraint, and deploy it to handle challenging visual tracking problems. …

    IEICE Transactions on Information and Systems E100.D(6), 1325-1338, 2017

    J-STAGE 

  • Inference of QoS Degradation Based on Spatial Dependence in Mobile Networks  [in Japanese]

    田行 里衣 , 金正 英朗 , 池上 大介 , 松田 崇弘 , 高橋 玲 , 滝根 哲哉

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 116(10), 1-6, 2016-04-21

  • An Alternative to Basic Log-Likelihood for Bayesian Network Clustering

    Rei Oshino , Koujin Takeda

    IEICE Proceeding Series (48), A3L-B-4, 2016

    DOI 

  • Emergence of active consciousness in working memory  [in Japanese]

    OSAKA Naoyuki

    … Theoretical modeling of consciousness using graph theory, with which we can quantify large-scale networks of the brain, supports our WM-based consciousness. … By introducing a false believe task, we confirmed high-level intentionality and meta-representation could also be involved in WM's executive function working on the dorsolateral PFC, which makes inference of another's mind possible. …

    Transactions of the Japan Academy 70(3), 135, 2016

    J-STAGE 

  • Bitwise MAP Estimation for Group Testing Based on Holographic Transformation

    WADAYAMA Tadashi , IZUMI Taisuke , MIMURA Kazushi

    … Our inference problem is to evaluate the posterior probabilities of the objects from the observation of <i>M</i>-test results and the prior probabilities for objects. … The derivation of the dual expression of posterior values can be naturally described based on a holographic transformation to the normal factor graph (NFG) representing the inference problem. …

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E99.A(12), 2147-2154, 2016

    IR  J-STAGE 

  • Sparse Trajectory Prediction Method Based on Entropy Estimation

    ZHANG Lei , LIU Leijun , LI Wen

    … Firstly, the moving region of trajectories is divided into a two-dimensional plane grid graph, and then the original trajectories are mapped to the grid graph so that each trajectory can be represented as a grid sequence. … Finally, under the new trajectory space, Markov model and Bayesian Inference is applied to trajectory prediction with data sparsity. …

    IEICE Transactions on Information and Systems E99.D(6), 1474-1481, 2016

    J-STAGE 

  • Stacking Approach to Temporal Relation Classification with Temporal Inference

    Laokulrat Natsuda , Miwa Makoto , Tsuruoka Yoshimasa

    … In this paper, we use timegraphs and stacked learning to perform temporal inference for classification in the temporal relation classification task. … Performing 10-fold cross-validation on the Timebank corpus, we achieve an F1 score of 60.25% using a graph-based evaluation, which is 0.90 percentage points higher than that of the local approach, outperforming other proposed systems. …

    Information and Media Technologies 11(0), 53-78, 2016

    J-STAGE 

  • Handling of Highly Symmetric Molecules for Chemical Structure Elucidation in a CAST/CNMR System

    KOICHI Shungo , KOSHINO Hiroyuki , SATOH Hiroko

    … In the course of the development of a system for NMR-based structure elucidation, we have developed a method for processing chemical structures with high symmetry by applying an efficient algorithm for graph inference. …

    Journal of Computer Chemistry, Japan 14(6), 193-195, 2016

    J-STAGE 

  • 22pBT-9 Community detection using asymptotic approximate Bayesian inference  [in Japanese]

    Hayashi Kohei , Konishi Takuya , Kawamoto Tatsuro

    Meeting Abstracts of the Physical Society of Japan 71.1(0), 3133, 2016

    J-STAGE 

Page Top