Search Results for author:
Found 2 papers, 0 papers with code
Exploring the Boundaries of On-Device Inference: When Tiny Falls Short, Go Hierarchical
In this context, the Hierarchical Inference (HI) system has emerged as a promising solution that augments the capabilities of the local ML by offloading selected samples to an edge server or cloud for remote ML inference.
The Case for Hierarchical Deep Learning Inference at the Network Edge
Depending on the application, if the inference provided by the local algorithm is incorrect or further assistance is required from large DL models on edge or cloud, only then the ED offloads the data sample.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
