Reproduce “Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mohamad Abou Ali, Fadi Dornaika
A systematic review maps the evolution of Edge Artificial Intelligence, proposing a novel multi-dimensional taxonomic framework to categorize its technologies, applications, and hardware. The work outlines the field's historical trajectory, current state-of-the-art, and future research directions, identifying key challenges and opportunities across diverse domains.
Key insights
- Edge AI's evolution represents a continuous drive for optimal efficiency, responsiveness, and scalability, shifting computational intelligence closer to data sources due to cloud limitations.
- The contemporary Edge AI ecosystem is characterized by a synergistic interplay of specialized hardware accelerators (ASICs, FPGAs, GPUs, Neuromorphic chips), optimized software frameworks (TensorFlow Lite, PyTorch Mobile), and efficient communication protocols (5G).
- Widespread adoption of Edge AI is hindered by interconnected systemic challenges including resource constraints, data privacy and security, complex model management, power consumption, and interoperability issues, necessitating fundamental trade-offs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.