Network In Network 网络解析

最新推荐文章于 2025-03-20 14:00:00 发布

心窄

最新推荐文章于 2025-03-20 14:00:00 发布

阅读量1k

点赞数 2

分类专栏：深度学习文章标签： Network In Network 网络解析 NIN

本文链接：https://blog.csdn.net/GL3_24/article/details/90400956

版权

Network In Network (NIN) 提出了一种新的深度网络结构，使用微神经网络代替传统线性滤波器增强局部建模能力。通过全局平均池化减少过拟合，提供更易于解释的分类结果。NIN在CIFAR-10和CIFAR-100等数据集上表现出优秀的分类性能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Network In Network

原文：https://arxiv.org/abs/1312.4400

Abstract：

We propose a novel deep network structure called “Network In Network”(NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input. Instead, we build micro neural networks with more complex structures to abstract the data within the receptive field. We instantiate the micro neural network with a multilayer perceptron, which is a potent function approximator. The feature maps are obtained by sliding the micro networks over the input in a similar manner as CNN; they are then fed into the next layer. Deep NIN can be implemented by stacking mutiple of the above described structure. With enh

最低0.47元/天解锁文章