arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.00864cs.LGphysics.ao-phphysics.data-anstat.ME
收藏

用于非线性回归的稠密连接神经网络

Densely connected neural networks for nonlinear regression

School of Mathematical and Statistical Sciences, Clemson University(克莱姆森大学数学与统计科学学院);Faculty of Engineering, Monash University(莫纳什大学工程学院);Faculty of Information Technology, Monash University(莫纳什大学信息技术学院);Institute of Atmospheric Physics, Chinese Academy of Sciences(中国科学院大气物理研究所)

Chao Jiang, Canchen Jiang, Dongwei Chen, Fei Hu

摘要:

密集连接卷积网络(DenseNet)在图像处理中表现良好。然而,对于回归任务,卷积DenseNet可能会丢失来自独立输入特征的基本信息。为了解决这个问题,我们提出了一种新的DenseNet回归模型,其中卷积和池化层被完全连接的层取代,并且保留了原始的连接快捷方式以重用该功能。为了研究深度和输入尺寸的影响,所提出的模型进行了仔细的验证,通过广泛的数值模拟。结果给出了最佳深度(19),并建议有限的输入尺寸(低于200)。与支持向量回归、决策树回归和残差回归等基线模型相比,最优深度模型的性能最好。最后,将DenseNet回归应用于相对湿度的预测,结果显示与观测值的相关性很高(0.91),这表明我们的模型可以促进环境数据分析。

英文摘要:

Densely connected convolutional networks (DenseNet) behave well in image processing. However, for regression tasks, convolutional DenseNet may lose essential information from independent input features. To tackle this issue, we propose a novel DenseNet regression model where convolution and pooling layers are replaced by fully connected layers and the original concatenation shortcuts are maintained to reuse the feature. To investigate the effects of depth and input dimension of proposed model, careful validations are performed by extensive numerical simulation. The results give an optimal depth (19) and recommend a limited input dimension (under 200). Furthermore, compared with the baseline models including support vector regression, decision tree regression, and residual regression, our proposed model with the optimal depth performs best. Ultimately, DenseNet regression is applied to predict relative humidity, and the outcome shows a high correlation (0.91) with observations, which indicates that our model could advance environmental data analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑