Considering the fact that students have different abilities to understand knowledge imparted by teachers, a multi-granularity distillation mechanism is proposed for transferring more understandable student networks. A self-analyzing module of teacher network designed, which enables learn from teaching patterns. Furthermore, stable excitation scheme robust supervision training. The can be embedd...

The method presented in this paper aims to reduce the computational costs of some kinds of navigation in a world with obstacles. We give algorithms to capture the logical structure of an object given a polygonal representation of it. Then these algorithms are used in conjunction with the notion of functional granularity to handle navigation of a moving object. 1 Framework The class of problems ...

The present many-to-many associative memory models can not carry out the multi-granularity association. In this paper some many-to-many multi-granularity associative memory models based on incidence of patterns are proposed by use of introducing logic calculation network and granularity control network. The model can control the granularity of output and carry out multi-granularity association.

Microservices have gained acceptance in software industries as an emerging architectural style for autonomic, scalable, and more reliable computing. Among the critical microservice architecture design decisions is when to adapt granularity of a by merging/decomposing microservices. No existing work investigates following question: How can we reason about trade-off between predicted benefits cos...

SaaS is a perfect technology to achieve scale economy. It uses multi-tenant to allow database to share storage but with irregular load, untraceable transaction characteristics and so on. TOL mechanism provides one granularity between the upper coarse-grained granularity and the lower finegrained granularity for each tenant. But the granularity may not be the most suitable. We define the cluster...