Maxout
2015-11-25 00:51
316 查看
Reading Paper-Network In Network(1)-Maxout
The maxout is designed to solve the problem that the representations that achieve good abstraction are generally highly nonlinear functions of the input data. Generally, the convolutional layers generate feature maps by liner convolutional filters followed by nonlinear activation functions. the feature map can be calculated as follows:
here it is a generalized linear model(GLM). However, some papers points that replacing the GLM with nonlinear function approximator can enhance the performance.
1 Maxout Network
For the maxout network, it adds another network between adjacent layers witch performs nonliner function to input data.
The maxout is designed to solve the problem that the representations that achieve good abstraction are generally highly nonlinear functions of the input data. Generally, the convolutional layers generate feature maps by liner convolutional filters followed by nonlinear activation functions. the feature map can be calculated as follows:
here it is a generalized linear model(GLM). However, some papers points that replacing the GLM with nonlinear function approximator can enhance the performance.
1 Maxout Network
For the maxout network, it adds another network between adjacent layers witch performs nonliner function to input data.
相关文章推荐
- 生活之行军蚁"死亡漩涡"
- Swift 2.0学习笔记(Day 3)——Swift 2.0之后增加的关键字
- web前端学习 11/24-25
- Socket的创建和连接
- 我是如何面试iOS开发者的?
- Qt学习之路(27): 渐变填充
- 内存页面管理
- LinearGradient线性渲染
- Angular 学习笔记——ng-disable
- 数组中不常用却又好用的方法探索
- Swift 2.0学习笔记(Day 2)——使用Web网站编写Swift代码
- QT 学习记录:渐变-QLinearGradient,QRadialGradient,QConicalGradient)
- MySQL解决中文乱码问题
- WebGL实现HTML5的3D贪吃蛇游戏
- 获取窗口最大值数组 O(n)解法
- 渗透测试项目一
- iOS子线程操作检测版本更新,防止阻塞住线程
- Online Judge判题结果解析
- 关于在struts2中利用jquery中如何动态从数据库中加载图片并显示
- C++之关键字认识累积