Edge AI and On-Device Inference to Reduce Cloud Dependency

Ravi kiran Gadiraju

Edge AI and On-Device Inference to Reduce Cloud Dependency

Authors

Ravi kiran Gadiraju

Keywords:

Edge AI; On-Device Inference; Cloud Dependency; Artificial Intelligence; Internet of Things (IoT); Model Compression; Real-Time Processing; Edge Computing; AI Accelerators; Federated Learning; Data Privacy; Embedded Systems; Low-Latency AI; Decentralized Intelligence; Neural Network Optimization

Abstract

The rapid proliferation of intelligent applications and the exponential growth of Internet of Things (IoT)devices have brought major drawbacks to cloud-centric AI paradigms, such as those of latency,consumption of bandwidth, data privacy and reliability of systems. Edge AI, understood as AI modelsbeing deployed on edge devices, changes the paradigm by allowing inference on the device with littleto no intervention from a centra

References

Premsankar, G., Di Francesco, M., & Taleb, T. (2018). Edge computing for the Internet of Things: A case study. IEEE Internet of Things Journal, 5(2), 1275–1284. https://doi.org/10.1109/JIOT.2018.2805263

Downloads

Published

2024-09-16

How to Cite

Ravi kiran Gadiraju. (2024). Edge AI and On-Device Inference to Reduce Cloud Dependency . Journal of Computational Analysis and Applications (JoCAAA), 33(08), 4538–4549. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/2863