Back to search

Georgia Institute of Technology

Robust Efficient Edge AI: New Principles and Frameworks for Empowering Artificial Intelligence on Edge Devices

Abstract

dc:description.abstract

Deep learning has revolutionised a breadth of industries by automating critical tasks while achieving superhuman accuracy. However, many of these benefits are driven by huge neural networks deployed on cloud servers that consume enormous energy. This thesis contributes two classes of novel frameworks and algorithms that extend the deployment frontier of deep learning models to tiny edge devices, which commonly operate in noisy environments with limited compute footprints: (1) New frameworks for efficient edge AI. We introduce methods that reduce inference cost through filter pruning and efficient network design. CUP presents a new method for compressing and accelerating models, by clustering and pruning similar filters in each layer. CMPNAS presents a new visual search framework that optimises a small and efficient edge model to work in tandem with a large server model to achieve high accuracy, achieving up to 80x compute cost reduction. (2) New methods for robust edge AI. We Introduce new methods that enable robustness to real-world noise while reducing inference cost. REST extends the scope of pruning to obtain networks that are 9x more efficient, run 5x faster and robust to adversarial and gaussian noise. HAR generalises the idea of early exiting in multi-branch neural networks to the training phase leading to networks that obtain state-of-the-art accuracy under class imbalance while saving up to 20% inference compute. IMBNAS optimises neural architectures on imbalanced datasets through super-network adaptation strategies that lead to 5x compute savings compared to searching from scratch. Our work makes a significant impact to industry and society: CMPNAS enables the edge deployment use-case for fashion and face retrieval services, and was highlighted at Amazon company-wide to thousands of researchers and developers. REST enables at-home sleep monitoring through a mobile phone and was highlighted by several news media.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Computer Science
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Duggal, Rahul
Advisors dc:contributor.advisor
  • Chau, Duen Horng
  • Sun, Jimeng
Committee members dc:contributor.committeemember
  • Vuduc, Richard
  • Gavrilovska, Ada
  • Hao, Callie

Subjects

dc:subject × 4

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/67315

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Duggal, Rahul. Robust Efficient Edge AI: New Principles and Frameworks for Empowering Artificial Intelligence on Edge Devices. Doctoral thesis, Georgia Institute of Technology, 2022. http://hdl.handle.net/1853/67315