EdgeAI: A Vision for Deep Learning in IoT Era
This work addresses the problem of enabling deep learning on resource-constrained IoT devices, but it is incremental as it builds on existing computation-aware methods and introduces new challenges without proven solutions.
The paper tackles the computational bottleneck of deploying deep learning on IoT devices by proposing EdgeAI, a new paradigm that addresses data-independent deployment and communication-aware distributed inference, but does not present concrete results or numbers.
The significant computational requirements of deep learning present a major bottleneck for its large-scale adoption on hardware-constrained IoT-devices. Here, we envision a new paradigm called EdgeAI to address major impediments associated with deploying deep networks at the edge. Specifically, we discuss the existing directions in computation-aware deep learning and describe two new challenges in the IoT era: (1) Data-independent deployment of learning, and (2) Communication-aware distributed inference. We further present new directions from our recent research to alleviate the latter two challenges. Overcoming these challenges is crucial for rapid adoption of learning on IoT-devices in order to truly enable EdgeAI.