Scholarlink

<p>Recent advancements in deep convolutional neural networks (CNNs) have revolutionized the fields of image processing, object detection, and image classification. Nevertheless, their performance is strongly architecture-dependent. Manually design optimal CNN architectures requires significant problem-understanding and domain-specific expertise, which is not necessarily available to everyone. Furthermore, this process is often very time-consuming and error-prone. Consequently, Neural Architecture Search (NAS) has emerged as a promising solution that aims to design optimal networks automatically. Unfortunately, many existing NAS methods require substantial human intervention and suffer from prohibitive search costs, particularly for resource-constrained applications. Besides, the optimal depth for a network is unknown and highly dependent on the complexity of the problem and the available data. To this end, this paper proposes a Fuzzy and Learning Automata-Guided method called FL-CNN, which leverages NSGA-II algorithm and is implemented using PyTorch in Python framework. Specifically, FL-CNN utilizes fuzzy logic to adaptively adjust crossover and mutation rates to avoid premature convergence and learning automata to improve diversity. Moreover, it presents a hybrid strategy for evaluating generated networks to reduce the excessively high search costs of NAS. Notably, FL-CNN achieves error rates of 2.6%, 12.1%, and 22.6% on CIFAR10, CIFAR100, and ImageNet datasets, respectively. Considering model complexity, FL-CNN generates networks with 0.17&#xa0;M, 1.1&#xa0;M, and 4.6&#xa0;M parameters, respectively. Despite achieving impressive performance, search cost for CIFAR10 and CIFAR100 datasets is 0.32 and 2.3 GPU Days, respectively. These results indicate that FL-CNN outperforms many existing evolutionary and non-evolutionary NAS methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An improved NSGA-II algorithm based on fuzzy logic and learning automata for automatically designing the convolutional neural network for image classification

  • 期刊论文

  • 发表日期：

    2025年5月19日

查看全文
  • Mahhya Alizadeh,
  • Seyed Mahdi Jameii,
  • Akram Reza

摘要

Recent advancements in deep convolutional neural networks (CNNs) have revolutionized the fields of image processing, object detection, and image classification. Nevertheless, their performance is strongly architecture-dependent. Manually design optimal CNN architectures requires significant problem-understanding and domain-specific expertise, which is not necessarily available to everyone. Furthermore, this process is often very time-consuming and error-prone. Consequently, Neural Architecture Search (NAS) has emerged as a promising solution that aims to design optimal networks automatically. Unfortunately, many existing NAS methods require substantial human intervention and suffer from prohibitive search costs, particularly for resource-constrained applications. Besides, the optimal depth for a network is unknown and highly dependent on the complexity of the problem and the available data. To this end, this paper proposes a Fuzzy and Learning Automata-Guided method called FL-CNN, which leverages NSGA-II algorithm and is implemented using PyTorch in Python framework. Specifically, FL-CNN utilizes fuzzy logic to adaptively adjust crossover and mutation rates to avoid premature convergence and learning automata to improve diversity. Moreover, it presents a hybrid strategy for evaluating generated networks to reduce the excessively high search costs of NAS. Notably, FL-CNN achieves error rates of 2.6%, 12.1%, and 22.6% on CIFAR10, CIFAR100, and ImageNet datasets, respectively. Considering model complexity, FL-CNN generates networks with 0.17 M, 1.1 M, and 4.6 M parameters, respectively. Despite achieving impressive performance, search cost for CIFAR10 and CIFAR100 datasets is 0.32 and 2.3 GPU Days, respectively. These results indicate that FL-CNN outperforms many existing evolutionary and non-evolutionary NAS methods.