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 system/network 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 betweenness 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.