Cost-informed Model Choice for On-device AI Applications

Authors

  • Reeshav Kumar

Keywords:

On-Device AI, Neural Network Quantization, Mobile AI Optimization, Energy-Efficient Inference, Edge Computing Constraints

Abstract

On-device AI deployment presents a set of unique challenges that are fundamentally different from thoseof cloud-based systems. These challenges necessitate specialized optimization approaches. Thedeployment must strike a balance between user experience and stringent resource constraints, including privacy preservation, energy

References

Andrew G. Howard et al., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," ResearchGate, April 2017.

https://www.researchgate.net/publication/316184205_MobileNets_Efficient_Convolutional_Neural_Net works_for_Mobile_Vision_Applications

Downloads

Published

2025-11-27

How to Cite

Reeshav Kumar. (2025). Cost-informed Model Choice for On-device AI Applications . Journal of Computational Analysis and Applications (JoCAAA), 34(11), 766–776. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/4251

Issue

Vol. 34 No. 11 (2025): JOCAAA

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.