1

Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder

Embedding models for entities and relations are extremely useful for recovering missing facts in a knowledge base. Intuitively, a relation can be modeled by a matrix mapping entity vectors. However, relations reside on low dimension sub-manifolds in …

オートエンコーダとの同時学習による知識共有

Learning Co-Substructures by Kernel Dependence Maximization

The automatic recognition of risks in traffic scenes is a core technology of Advanced Driver Assistance Systems (ADASs). Most of the existing work on traffic risk recognition has been conducted in the context of motion prediction of vehicles. Thus, …

独立性尺度に基づく知識の粒度の教師なし推定

Modeling the association between items in a dataset is a problem that is frequently encountered in data and knowledge mining research. Most previous studies have simply applied a predefined fixed pattern to extract the substructure of each item pair …

交通オントロジーと説明生成に基づく交通危険予測

We develop an Advanced Driver Assistance System (ADAS) that can recognize potential risks in traffic scenes and provide the reasoning for its prediction. In this study, we extend our previous risk prediction model combining logic-based reasoning with …