Automatic Convolutional Neural Network Selection for Image Classification Using Genetic Algorithms
Automatic Convolutional Neural Network Selection for Image Classification Using Genetic Algorithms
复制标题
使用遗传算法进行图像分类的自动卷积神经网络选择
DOI：
10.1109/iri.2018.00071
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Sitharama S. Iyengar
中科院分区：
文献类型：
--
作者：
Haiman Tian;Samira Pouyanfar;Jonathan Chen;Shu‐Ching Chen;Sitharama S. Iyengar
卷积神经网络（cnn）等深度神经网络在视觉数据分析方面取得了几个重要的里程碑。受益于迁移学习，许多研究人员使用预训练的CNN模型来加速训练过程。然而，深度学习的模型、结构和应用仍然存在不确定性。例如，数据集的多样性可能会影响每个预训练模型的性能。因此，在本文中，我们提出了一种基于遗传算法的新方法，针对不同的视觉数据集选择或再生最佳的预训练CNN模型。提出了一种新的遗传编码模型，表示不同的预训练模型在我们的群体。在进化过程中，选择代表最佳模型的最优遗传密码，或通过遗传操作产生新的竞争个体。实验结果表明，该框架在视觉数据分类方面优于现有的几种方法。
Deep neural networks such as Convolutional Neural Networks (CNNs) have achieved several significant milestones in visual data analytics. Benefited from transfer learning, many researchers use pre-trained CNN models to accelerate the training process. However, there is still uncertainty about the deep learning models, structures, and applications. For instance, the diversity of the datasets may affect the performance of each pre-trained model. Therefore, in this paper, we proposed a new approach based on genetic algorithms to select or regenerate the best pre-trained CNN models for different visual datasets. A new genetic encoding model is presented which denotes different pre-trained models in our population. During the evolutionary process, the optimal genetic code that represents the best model is selected, or new competitive individuals are generated using the genetic operations. The experimental results illustrate the effectiveness of the proposed framework which outperforms several existing approaches in visual data classification.