Delocalizing AI with Emerging Edge Intelligence (IoT/Internet)
Advances in artificial intelligence (AI)are transforming science and technologies. However, the exploding computational demands of the most powerful AI algorithms lead to serious energy pitfalls. This trend is further accelerated by the simultaneous move towards trillions of intelligent edge devices. Several efforts are underway to address this challenge which includes in-memory computing, neuromorphic computing, silicon photonics architecture, etc. In this special session, we intend to showcase five eminent research talks covering circuit-level innovation, system-level optimization, network-level creativity, and algorithmic codesign for next-generation edge-intelligence systems. A major goal of this session is to bring communities together embarking a pathway towards decentralizing AI in edge infrastructure with secured and energy-efficient computing.
Error Correction and Detection for Analog AI Computing at the Edge
Codesigning 2.5D Photonic Accelerator for Distributed Transformer at the Edge
A Materials- and Devices-Centric Approach Toward Neuromorphic Computing
Fault Tolerant In-Memory Computing based on Emerging Technologies for Ultra-Low Precision Edge AI Accelerators