Distributed Deep Convolutional Neural Networks for the Internet-of-Things
This addresses the problem of enabling real-time deep learning applications for IoT systems, though it appears incremental as it builds on existing distributed computing and optimization techniques.
The paper tackles the challenge of running deep learning models on resource-constrained IoT devices by proposing a design methodology to distribute Convolutional Neural Networks across IoT units, minimizing latency between data gathering and decision-making while adhering to memory and processing constraints.
Severe constraints on memory and computation characterizing the Internet-of-Things (IoT) units may prevent the execution of Deep Learning (DL)-based solutions, which typically demand large memory and high processing load. In order to support a real-time execution of the considered DL model at the IoT unit level, DL solutions must be designed having in mind constraints on memory and processing capability exposed by the chosen IoT technology. In this paper, we introduce a design methodology aiming at allocating the execution of Convolutional Neural Networks (CNNs) on a distributed IoT application. Such a methodology is formalized as an optimization problem where the latency between the data-gathering phase and the subsequent decision-making one is minimized, within the given constraints on memory and processing load at the units level. The methodology supports multiple sources of data as well as multiple CNNs in execution on the same IoT system allowing the design of CNN-based applications demanding autonomy, low decision-latency, and high Quality-of-Service.