论文标题
深神经网络中的汇总方法，评论
Pooling Methods in Deep Neural Networks, a Review
论文作者
论文摘要
如今，深度神经网络是各种科学中使用的主要工具之一。卷积神经网络是一种特殊的DNN类型，由几个卷积层组成，每个卷积层随后是一个激活函数和一个合并层。合并层是一个重要的层，它可以在上一层的特征图上执行向下采样，并以冷凝分辨率生成新的特征地图。该层大大降低了输入的空间维度。它有两个主要目的。首先是减少参数或权重的数量，从而减少计算成本。第二个是控制网络的过度拟合。理想的合并方法有望仅提取有用的信息并丢弃无关紧要的细节。在深神经网络中实施合并操作有很多方法。在本文中，我们回顾了一些著名且有用的汇总方法。
Nowadays, Deep Neural Networks are among the main tools used in various sciences. Convolutional Neural Network is a special type of DNN consisting of several convolution layers, each followed by an activation function and a pooling layer. The pooling layer is an important layer that executes the down-sampling on the feature maps coming from the previous layer and produces new feature maps with a condensed resolution. This layer drastically reduces the spatial dimension of input. It serves two main purposes. The first is to reduce the number of parameters or weights, thus lessening the computational cost. The second is to control the overfitting of the network. An ideal pooling method is expected to extract only useful information and discard irrelevant details. There are a lot of methods for the implementation of pooling operation in Deep Neural Networks. In this paper, we reviewed some of the famous and useful pooling methods.
