We propose a learning architecture for integrating multi-modal information e.g., vision, audio information. In recent years, artificial intelligence (AI) is making major progress in key tasks like a language, vision, ...We propose a learning architecture for integrating multi-modal information e.g., vision, audio information. In recent years, artificial intelligence (AI) is making major progress in key tasks like a language, vision, voice recognition tasks. Most studies focus on how AI could achieve human-like abilities. Especially, in human-robot interaction research field, some researchers attempt to make robots talk with human in daily life. The key challenges for making robots talk naturally in conversation are to need to consider multi-modal non-verbal information same as human, and to learn with small amount of labeled multi-modal data. Previous multi-modal learning needs a large amount of labeled data while labeled multi-modal data are shortage and difficult to be collected. In this research, we address these challenges by integrating single-modal classifiers which trained each modal information respectively. Our architecture utilized knowledge by using bi-directional associative memory. Furthermore, we conducted the conversation experiment for collecting multi-modal non-verbal information. We verify our approach by comparing accuracies between our system and conventional system which trained multi-modal information.展开更多
Articular cartilage has a unique collagen fibre network structure that exhibits both anisotropy and depth dependency.Collagen fibre orientation in a cross-section parallel to the articular cartilage surface may affect...Articular cartilage has a unique collagen fibre network structure that exhibits both anisotropy and depth dependency.Collagen fibre orientation in a cross-section parallel to the articular cartilage surface may affect the lubrication properties of articular cartilage.The effect of collagen fibre orientation on the frictional properties of articular cartilage was examined through finite element analysis of the friction.Specifically,a three-dimensional fibre-reinforced poroelastic biphasic model was used to determine the influence of collagen fibril orientation on the frictional properties of articular cartilage.The simulations reveal that collagen fibre orientation has a significant influence on the deformation behaviour of articular cartilage in front of and behind the contact area.The coefficient of dynamic friction was lower in the direction parallel to the collagen fibre orientation than in the direction perpendicular to the collagen fibre orientation,regardless of the indenter speed.展开更多
文摘We propose a learning architecture for integrating multi-modal information e.g., vision, audio information. In recent years, artificial intelligence (AI) is making major progress in key tasks like a language, vision, voice recognition tasks. Most studies focus on how AI could achieve human-like abilities. Especially, in human-robot interaction research field, some researchers attempt to make robots talk with human in daily life. The key challenges for making robots talk naturally in conversation are to need to consider multi-modal non-verbal information same as human, and to learn with small amount of labeled multi-modal data. Previous multi-modal learning needs a large amount of labeled data while labeled multi-modal data are shortage and difficult to be collected. In this research, we address these challenges by integrating single-modal classifiers which trained each modal information respectively. Our architecture utilized knowledge by using bi-directional associative memory. Furthermore, we conducted the conversation experiment for collecting multi-modal non-verbal information. We verify our approach by comparing accuracies between our system and conventional system which trained multi-modal information.
基金This work was supported by JSPS KAKENHI Grant No.JP16H03172.
文摘Articular cartilage has a unique collagen fibre network structure that exhibits both anisotropy and depth dependency.Collagen fibre orientation in a cross-section parallel to the articular cartilage surface may affect the lubrication properties of articular cartilage.The effect of collagen fibre orientation on the frictional properties of articular cartilage was examined through finite element analysis of the friction.Specifically,a three-dimensional fibre-reinforced poroelastic biphasic model was used to determine the influence of collagen fibril orientation on the frictional properties of articular cartilage.The simulations reveal that collagen fibre orientation has a significant influence on the deformation behaviour of articular cartilage in front of and behind the contact area.The coefficient of dynamic friction was lower in the direction parallel to the collagen fibre orientation than in the direction perpendicular to the collagen fibre orientation,regardless of the indenter speed.
