Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Codesign

Abstract

Artificial intelligence (AI) technologies have dramatically advanced in recent years, resulting in revolutionary changes in people's lives. Empowered by edge computing, AI workloads are migrating from centralized cloud architectures to distributed edge systems, introducing a new paradigm called edge AI. While edge AI has the promise of bringing significant increases in autonomy and intelligence into everyday lives through common edge devices, it also raises new challenges, especially for the development of its algorithms and the deployment of its services, which call for novel design methodologies catered to these unique challenges. In this paper, we provide a comprehensive survey of the latest enabling design methodologies that span the entire edge AI development stack. We suggest that the key methodologies for effective edge AI development are single-layer specialization and cross-layer co-design. We discuss representative methodologies in each category in detail, including on-device training methods, specialized software design, dedicated hardware design, benchmarking and design automation, software/hardware co-design, software/compiler co-design, and compiler/hardware co-design. Moreover, we attempt to reveal hidden cross-layer design opportunities that can further boost the solution quality of future edge AI and provide insights into future directions and emerging areas that require increased research focus.

Security and Privacy for Edge Artificial Intelligence

“…What do such systems portend for the specification and implementation of policy and mechanisms for security and privacy? E dge AI is a burgeoning area of research and development, in part because the enabling technologies are becoming available, such as 5G networks, high-performance AI chips, 5 lightweight AI models, AI-specific service architectures for the edge, 6 co-design methodologies tailored for edge computing and edge AI, 7 and lightweight and leakage-resilient authenticated key exchange protocols for edge AI. 8 mobile edge networks of heterogeneous devices while preserving the privacy of the data of each of the participants (edge nodes) that are taking part in FL in the presence of one or more malicious participants or aggregators (servers).…”

Modeling an Edge Computing Arithmetic Framework for IoT Environments

“…The development of IoT (Internet of Things) technologies are sharply rising in recent times, thanks to the advances in AI (Artificial Intelligence) and its application to MEC (Multi-Access Edge Computing) environments [1]. This union of both concepts is labelled as Edge AI [2], which brings about powerful data centres to carry out many complex computing tasks in servers located around the edge of the network, as opposed to in those situated up in the cloud premises, thus enhancing performance [3].…”

PhiNets: A Scalable Backbone for Low-power AI at the Edge

“…On the other side, with the advent of deep learning techniques, machine learning algorithms' size grows exponentially, thanks to the improvements in processor speeds and the availability of large training data. However, embedded systems cannot sustain the resource requirements of standard deep learning techniques, adequate for GP-GPUs [6,14,33].…”