[Read Paper] Maxout Networks
2016-01-16 22:31
190 查看
Title: Maxout Networks
Author: Ian J. Goodfellow, David Warde-Farley Mehdi Mirza et al.
摘要:
We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout’s fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN.
全文链接:http://arxiv.org/abs/1302.4389
Note:
The maxout model is simply a feed-forward achitecture, such as a multilayer perceptron or deep convolutional neural network, that uses a new type of activation function: the maxout unit.
Given an input x , a maxout hidden layer implements the function
Author: Ian J. Goodfellow, David Warde-Farley Mehdi Mirza et al.
摘要:
We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout’s fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN.
全文链接:http://arxiv.org/abs/1302.4389
Note:
The maxout model is simply a feed-forward achitecture, such as a multilayer perceptron or deep convolutional neural network, that uses a new type of activation function: the maxout unit.
Given an input x , a maxout hidden layer implements the function
相关文章推荐
- oop
- 如何提升内容的价值
- 【php】 勾搭 Composer\Autoload\ClassLoader 类
- 利用java语言将csv格式数据导入mysql数据库
- 【转】Oracle的伪列
- 【转】ORACLE的HINT详解
- BZOJ 4276 费用流+线段树构图
- 前端面试题
- 我眼中的《少帅》
- IIS中利用ARR实现反向代理初探
- Java异常笔记整理
- python 函数重载
- MySQL函数大全系列(字符串操作)
- Imx6q Andriod5.1.2
- bzoj1876 SuperGCD
- HDOJ1205(吃糖果)
- http详解
- java 中byte[] 数组的合并
- SQL---Case
- ERDAS IMAGINE 2014 32位 破解安装