卷积神经网络
计算机科学
核(代数)
公制(单位)
人工智能
进化算法
机器学习
建筑
过程(计算)
人工神经网络
模式识别(心理学)
工程类
数学
艺术
运营管理
组合数学
视觉艺术
操作系统
作者
Junqi Huang,Bing Xue,Yanan Sun,Mengjie Zhang
标识
DOI:10.1145/3583133.3590535
摘要
With the increasing demand of deploying convolutional neural networks (CNNs) on resource-constrained devices, designing high-performance and lightweight architectures has become a main challenge for neural architecture search (NAS). This paper develops an evolutionary multi-objective optimization framework to explore CNNs with different compactness in a flexible way. A multi-scale convolutional module is developed to enhance the feature learning capability. To further improve the architecture search efficiency, a low-cost metric based on neural tangent kernel is leveraged to estimate the trainability of CNNs instead of performing an expensive training process. Experiments are carried out on CIFAR-10 and CIFAR-100, to verify the effectiveness of the proposed method. Compared with the state-of-the-art algorithms, the proposed method discovers architectures with a smaller number of parameters and competitive classification performance using only up to 0.2 GPU days, showing a better trade-off between accuracy and model complexity.
科研通智能强力驱动
Strongly Powered by AbleSci AI