Reviewing and Discussing Graph Reduction in Edge Computing Context

Much effort has been devoted to transferring efficiently different machine-learning algorithms, and especially deep neural networks, edge devices in order fulfill, among others, real-time, storage energy-consumption issues. The limited resources of the necessity for energy saving lengthen durability their batteries, encouraged an interesting trend reducing networks graphs, while keeping predictability almost untouched. In this work, alternative latest techniques finding these reductions size is proposed, seeking figure out a simplistic way shrink maintaining, as far possible, testing on well-known datasets.