tinyML Talks: Energy-Efficiency and Security for TinyML and EdgeAI: A Cross-Layer Approach
“Energy-Efficiency and Security for TinyML and EdgeAI: A Cross-Layer Approach”
Prof. Dr. Muhammad Shafique
Department of Electrical and Computer Engineering (ECE)
New York University Abu Dhabi (NYUAD), UAE
ECE, Tandon School of Engineering
New York University (NYU), USA
Co-PI / Co-Investigator in Center of Artificial Intelligence and Robotics (CAIR), Center of Cyber Security (CCS)
Center for InTeractIng urban nEtworkS (CITIES), and Center for Quantum and Topological Systems
Modern Machine Learning (ML) approaches like Deep Neural Networks (DNNs) have shown tremendous improvement over the past years to achieve a significantly high accuracy for a certain set of tasks, like image classification, object detection, natural language processing, and medical data analytics. However, these DNN require huge processing, memory, and energy costs, besides being vulnerable to several security threats. This talk will present challenges and cross-layer frameworks for building highly energy-efficient and robust machine learning systems for the tinyML and EdgeAI applications, which jointly leverage optimizations at different software and hardware layers, e.g., neural accelerator, memory access optimizations, approximations, hardware-aware NAS and network compression. These cross-layer techniques enable new opportunities for improving the area, power/energy, and performance efficiency of systems by orders of magnitude, which is a crucial step towards enabling the wide-scale deployment of resource-constrained embedded AI systems like UAVs, autonomous vehicles, Robotics, IoT-Healthcare / Wearables, Industrial-IoT, etc.
source
