一种改进池化模型对卷积神经网络性能影响的研究
|
摘要
池化模型作为卷积神经网络模型中至关重要的一部分,具有降维、提高模型泛化能力等作用。为了进一步提高卷积神经网络模型的准确率,优化模型的学习性能,提出了一种基于最大池化和平均池化的改进池化模型,并在全球手写数字数据集MNIST和CIFAR-10上分别对改进池化模型的有效性进行了验证。通过与常见池化模型的对比实验发现,采用改进池化模型的卷积神经网络的学习性能较优,一次迭代情况下,在MNIST和CIFAR-10数据集上,错误率分别下降了4.28%和2.15%。
As a vital part of the convolutional neural network model, the pooling model has the functions of dimension reduction and generalization of the model. In order to further improve the accuracy of the convolutional neural network model and optimize the learning performance of the model, this paper proposes an improved pooling model based on maximum pooling and average pooling, and the global handwritten digital datasets MNIST and CIFAR-10 data. The effectiveness of the improved pooling model was verified on the two dataset. Comparing with the common pooling model, it is found that the learning performance of the convolutional neural network with improved pooling model is better. In one iteration, the error rate decreases by 4.28% on the MNIST and decreases by 2.15% on CIFAR-10 datasets.
As a vital part of the convolutional neural network model, the pooling model has the functions of dimension reduction and generalization of the model. In order to further improve the accuracy of the convolutional neural network model and optimize the learning performance of the model, this paper proposes an improved pooling model based on maximum pooling and average pooling, and the global handwritten digital datasets MNIST and CIFAR-10 data. The effectiveness of the improved pooling model was verified on the two dataset. Comparing with the common pooling model, it is found that the learning performance of the convolutional neural network with improved pooling model is better. In one iteration, the error rate decreases by 4.28% on the MNIST and decreases by 2.15% on CIFAR-10 datasets.
引文
[1] 刘万军,梁雪剑,曲海成.不同池化模型的卷积神经网络学习性能研究[J].中国图象图形学报,2016,21(9):1178-1190.
[2] ALEX K, ILYA S, HINTON G E. ImageNet classification with deep convolutional neural networks[EB/OL].[2015-02-10].http://papers.nips.cc/paper/4824-imagenet-classification-withdeep-convolutional-neural-networks.Pdf.
[3] LEE H, GROSSE R, RANGANATH R, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[C]. Proceedings of the 26th Annual International Conference on Machine Learning, ACM, 2009:609-616.
[4] GONG Y C, WANG L W, GUO R Q, et al. Multi-scale orderless pooling of deep convolutional activation features[C]. Proceedings of the 13th European Conference on Computer Vision, Springer, 2014: 392-407.
[5] 史鹤欢,许悦雷,马时平,等.PCA预训练的卷积神经网络目标识别算法[J].西安电子科技大学学报,2016,43(3):161-166.
[6] 张贵勇.改进的卷积神经网络在金融预测中的应用研究[D].郑州:郑州大学,2016.
[7] 李媛媛.卷积神经网络优化及其在图像识别中的应用[D].沈阳:沈阳工业大学,2016.
[8] 刘梦雅,毛剑琳.基于灰度关联分析法的卷积神经网络算法优化[J].电子科技,2018,31(6):84-88,95.
[9] 张文达,许悦雷,倪嘉成,等.基于多尺度分块卷积神经网络的图像目标识别算法[J].计算机应用,2016,36(4):1033-1038.
[10] 蒋帅.基于卷积神经网络的图像识别[D].长春:吉林大学,2017.
[11] 余萍,赵继生.基于矩阵2-范数池化的卷积神经网络图像识别算法[J].图学学报,2016,37(5):694-701.
[12] 时增林.深度卷积神经网络中基于序的池化方法研究[D].郑州:郑州大学,2017.
[13] 曹容川.图像分类中基于显著关系的改进特征编码与池化算法研究[D].长春:吉林大学,2017.
[14] 孙峰,龚晓玲,张炳杰,等.一种基于共轭梯度法的广义单隐层神经网络[J].郑州大学学报(工学版),2018,39(2):28-32.
[15] 崔华,刘云飞,宋鑫鑫,等.基于CNN深度学习模型的交通图像拥堵识别[J].科技创新与应用,2018(4):19-20,22.
[2] ALEX K, ILYA S, HINTON G E. ImageNet classification with deep convolutional neural networks[EB/OL].[2015-02-10].http://papers.nips.cc/paper/4824-imagenet-classification-withdeep-convolutional-neural-networks.Pdf.
[3] LEE H, GROSSE R, RANGANATH R, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[C]. Proceedings of the 26th Annual International Conference on Machine Learning, ACM, 2009:609-616.
[4] GONG Y C, WANG L W, GUO R Q, et al. Multi-scale orderless pooling of deep convolutional activation features[C]. Proceedings of the 13th European Conference on Computer Vision, Springer, 2014: 392-407.
[5] 史鹤欢,许悦雷,马时平,等.PCA预训练的卷积神经网络目标识别算法[J].西安电子科技大学学报,2016,43(3):161-166.
[6] 张贵勇.改进的卷积神经网络在金融预测中的应用研究[D].郑州:郑州大学,2016.
[7] 李媛媛.卷积神经网络优化及其在图像识别中的应用[D].沈阳:沈阳工业大学,2016.
[8] 刘梦雅,毛剑琳.基于灰度关联分析法的卷积神经网络算法优化[J].电子科技,2018,31(6):84-88,95.
[9] 张文达,许悦雷,倪嘉成,等.基于多尺度分块卷积神经网络的图像目标识别算法[J].计算机应用,2016,36(4):1033-1038.
[10] 蒋帅.基于卷积神经网络的图像识别[D].长春:吉林大学,2017.
[11] 余萍,赵继生.基于矩阵2-范数池化的卷积神经网络图像识别算法[J].图学学报,2016,37(5):694-701.
[12] 时增林.深度卷积神经网络中基于序的池化方法研究[D].郑州:郑州大学,2017.
[13] 曹容川.图像分类中基于显著关系的改进特征编码与池化算法研究[D].长春:吉林大学,2017.
[14] 孙峰,龚晓玲,张炳杰,等.一种基于共轭梯度法的广义单隐层神经网络[J].郑州大学学报(工学版),2018,39(2):28-32.
[15] 崔华,刘云飞,宋鑫鑫,等.基于CNN深度学习模型的交通图像拥堵识别[J].科技创新与应用,2018(4):19-20,22.