# Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence

## TL;DR

This paper introduces a PCA-driven method to design mixed-precision neural networks that significantly improve accuracy over binary networks while maintaining high energy efficiency for edge computing applications.

## Contribution

It presents a novel PCA-based approach to identify important layers and create mixed-precision networks, enhancing performance of compressed neural networks on edge devices.

## Key findings

- Over 10% accuracy improvement over binary networks like XNOR-Net.
- Achieves up to 94% of the energy efficiency of XNOR-Nets.
- Effective on ResNet and VGG architectures for CIFAR-100 and ImageNet.

## Abstract

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.