The Case for Hierarchical Deep Learning Inference at the Network Edge

no code implementations • 23 Apr 2023 • Ghina Al-Atat, Andrea Fresa, Adarsh Prasad Behera, Vishnu Narayanan Moothedath, James Gross, Jaya Prakash Champati

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.

Fault Detection Image Classification

Online Algorithms for Hierarchical Inference in Deep Learning applications at the Edge

no code implementations • 3 Apr 2023 • Vishnu Narayanan Moothedath, Jaya Prakash Champati, James Gross

In order to get the best out of both worlds, i. e., the benefits of doing inference on the ED and the benefits of doing inference on ES, we explore the idea of Hierarchical Inference (HI), wherein S-ML inference is only accepted when it is correct, otherwise the data sample is offloaded for L-ML inference.

Image Classification Meta-Learning