The different CNN models use many layers that typically include a stack of linear convolution layers combined with pooling and normalization layers to extract the characteristics of the images. Unlike these models, and instead of using a linear filter for convolution, the network in network (NiN) model uses a multilayer perception (MLP), a nonlinear function, to replace the linear filter. This article presents a new deep network in network (DNIN) model based on the NiN structure, NiN drag a universal approximator, (MLP) with rectified linear unit (ReLU) to improve classification performance. The use of MLP leads to an increase in the density of the connection. This makes learning more difficult and time learning slower. In this article, instead of ReLU, we use the linear exponential unit (eLU) to solve the vanishing gradient problem that can occur when using ReLU and to speed up the learning process. In addition, a reduction in the convolution filters size by increasing the depth is used in order to reduce the number of parameters. Finally, a batch normalization layer is applied to reduce the saturation of the eLUs and the dropout layer is applied to avoid overfitting. The experimental results on the CIFAR-10 database show that the DNIN can reduce the complexity of implementation due to the reduction in the adjustable parameters. Also the reduction in the filters size shows an improvement in the recognition accuracy of the model.

不同的CNN模型使用许多层，通常包括一堆线性卷积层以及合并和归一化层，以提取图像的特征。与这些模型不同，网络中的网络（NiN）模型不是使用线性滤波器进行卷积，而是使用一种非线性函数多层感知（MLP）来代替线性滤波器。本文提出了一种基于NiN结构的新型深层网络（DNIN）模型，NiN拖动了带有整流线性单元（ReLU）的通用逼近器（MLP），以提高分类性能。使用MLP会导致连接密度增加。这使学习更加困难，时间学习也变慢。在本文中，代替ReLU，我们使用线性指数单位（eLU）解决了使用ReLU时可能出现的消失梯度问题，并加快了学习过程。另外，为了减少参数的数量，使用了通过增加深度来减小卷积滤波器的尺寸。最后，应用批处理归一化层以降低eLU的饱和度，并应用辍学层以避免过度拟合。在CIFAR-10数据库上的实验结果表明，由于可调参数的减少，DNIN可以降低实现的复杂性。滤波器尺寸的减小也显示了模型识别精度的提高。为了减少参数的数量，使用了通过增加深度来减少卷积滤波器尺寸的方法。最后，应用批处理归一化层以降低eLU的饱和度，并应用辍学层以避免过度拟合。在CIFAR-10数据库上的实验结果表明，由于可调参数的减少，DNIN可以降低实现的复杂性。滤波器尺寸的减小也显示了模型识别精度的提高。为了减少参数的数量，使用了通过增加深度来减少卷积滤波器尺寸的方法。最后，应用批处理归一化层以降低eLU的饱和度，并应用辍学层以避免过度拟合。在CIFAR-10数据库上的实验结果表明，由于可调参数的减少，DNIN可以降低实现的复杂性。滤波器尺寸的减小也显示了模型识别精度的提高。