Influence of a Topology of a Spring Network on its Ability to Learn Mechanical Behaviour

摘要

We discuss how the topology of the spring systemetwork affects its ability to learn a desired mechanical behaviour. To ensure such a behaviour, physical parameters of springs of the system are adjusted by an appropriate gradient descent learning algorithm. We find the between-ness centrality measure particularly convenient to describe topology of the spring system structure with the best mechanical properties. We apply our results to refine an algorithm generating the structure of a spring network. We also present numerical results confirming our statements.