Multi-Component Optimization and Efficient Deployment of Neural-Networks on Resource-Constrained IoT Hardware
This enables offline AI analytics on IoT devices, addressing issues like latency and privacy, though it is incremental as it builds on existing optimization techniques.
The paper tackles the problem of deploying large neural networks on resource-constrained IoT devices by presenting a multi-component optimization sequence, resulting in models that are 12.06x compressed, 0.13% to 0.27% more accurate, and achieve inference at 0.06 ms.
The majority of IoT devices like smartwatches, smart plugs, HVAC controllers, etc., are powered by hardware with a constrained specification (low memory, clock speed and processor) which is insufficient to accommodate and execute large, high-quality models. On such resource-constrained devices, manufacturers still manage to provide attractive functionalities (to boost sales) by following the traditional approach of programming IoT devices/products to collect and transmit data (image, audio, sensor readings, etc.) to their cloud-based ML analytics platforms. For decades, this online approach has been facing issues such as compromised data streams, non-real-time analytics due to latency, bandwidth constraints, costly subscriptions, recent privacy issues raised by users and the GDPR guidelines, etc. In this paper, to enable ultra-fast and accurate AI-based offline analytics on resource-constrained IoT devices, we present an end-to-end multi-component model optimization sequence and open-source its implementation. Researchers and developers can use our optimization sequence to optimize high memory, computation demanding models in multiple aspects in order to produce small size, low latency, low-power consuming models that can comfortably fit and execute on resource-constrained hardware. The experimental results show that our optimization components can produce models that are; (i) 12.06 x times compressed; (ii) 0.13% to 0.27% more accurate; (iii) Orders of magnitude faster unit inference at 0.06 ms. Our optimization sequence is generic and can be applied to any state-of-the-art models trained for anomaly detection, predictive maintenance, robotics, voice recognition, and machine vision.