Split CNN Inference on Networked Microcontrollers

ArXi:2605.09357v1 Announce Type: cross Running deep neural networks on microcontroller units (MCUs) is severely constrained by limited memory resources. While TinyML techniques reduce model size and computation, they often fail in practice due to excessive peak Random Access Memory (RAM) usage during inference, dominated by intermediate activations. As a result, many models remain infeasible on standalone MCUs.