Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence
This work addresses the problem of balancing accuracy and energy-efficiency for AI on edge devices, representing an incremental advance in quantization techniques.
The paper tackles the performance loss in quantized neural networks for edge computing by proposing a PCA-driven method to design mixed-precision networks, achieving over 10% accuracy improvement over binary networks like XNOR-Net on CIFAR-100 and ImageNet while maintaining up to 94% energy-efficiency.
The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles. Quantization is a powerful tool to address the growing computational cost of such applications, and yields significant compression over full-precision networks. However, quantization can result in substantial loss of performance for complex image classification tasks. To address this, we propose a Principal Component Analysis (PCA) driven methodology to identify the important layers of a binary network, and design mixed-precision networks. The proposed Hybrid-Net achieves a more than 10% improvement in classification accuracy over binary networks such as XNOR-Net for ResNet and VGG architectures on CIFAR-100 and ImageNet datasets while still achieving up to 94% of the energy-efficiency of XNOR-Nets. This work furthers the feasibility of using highly compressed neural networks for energy-efficient neural computing in edge devices.