Techniques for preventing overfitting in training Deep Neural Networks
来源:互联网 发布:php 整数保留2位小数 编辑:程序博客网 时间:2024/06/05 12:43
Techniques for preventing overfitting in training Deep Neural Networks
Data
Data Augmentation
- data cropping
- adding noise to data
- affine warping to data.
Model Regularization
Dropout
Consider deep neural networks that contain a series of hidden layers h = {h1,..., hL}, and predict output y given input x. Dropout is a technique that trains an ensemble of models consisting a subset of variables in h, or even x. On each presentation of a training sample, we train a different sub-model taking a random subset of variable h. Technically speaking, we randomly set hidden variables to zeros according to some probabilities. Thus each sample sees a different model to prevent co-adaptation of features.
Dropout training is similar to bagging, where many different models are trained on different subsets of the data. Dropout differs from bagging in that each model is trained for only one step and all the models share parameters.
- G. E. Hinton. Improving neural networks by preventing co-adaptation of feature detectors
Maxout
Maxout is also a technique for model-averaging, which a natural companion to dropout. Maxout takes the max of a set of inputs. It's particular applicable for convolutional neural networks. In a convolutional neural network , a maxout feature map can be constructed by taking the maximum across k affine feature maps (i.e. pool across channels).
- Ian J. Goodfellow, Yoshua Bengio. Maxout Networks
Drop connection
DropConnect is the generalization of Dropout in which each connection, rather than each output unit, can be dropped with probability. DropConnect is similar to Dropout as it introduces dynamic sparsity within the model, but differs in that the sparsity is on the weights W, rather than the output vectors of a layer. In other words, the fully connected layer with DropConnect becomes a sparsely connected layer in which the connections are chosen at random during the training stage.
- Li Wan. Regularization of Neural Networks using DropConnect
- Techniques for preventing overfitting in training Deep Neural Networks
- Efficient Training of Very Deep Neural Networks for Supervised Hashing
- Training Deep Convolutional Neural Networks for Land–Cover Classification of High-Resolution Imagery
- Deep Learning in Neural Networks: An Overview
- Learning Structured Sparsity in Deep Neural Networks
- Deep Neural Networks for YouTube Recommendations
- Deep Learning读书笔记(六):Improving neural networks by preventing co-adaptation of feature detectors
- Understanding the difficulty of training deep feedforward neural networks
- Understanding the difficulty of training deep feedforward neural networks (Xavier)
- BinaryConnect: Training Deep Neural Networks with binary weights during propagations
- 《Understanding the difficulty of training deep feedforward neural networks》笔记
- BinaryConnect: Training Deep Neural Networks with binary weights during propagations
- Understanding the difficulty of training deep feedforward neural networks
- 论文笔记 Ensemble of Deep Convolutional Neural Networks for Learning to Detect Retinal Vessels in Fundus
- an empirical study of learning rates in deep neural networks for speech recognition 总结
- 车辆计数“FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras”
- 车辆计数--FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
- Deep learning-------------Neural networks
- TAR命令的基本使用方法详解
- unity3d math 常用的数学
- hdu4973(线段树)
- SpringMVC一次请求多次进入Control的原因
- poj 2983 差分约束
- Techniques for preventing overfitting in training Deep Neural Networks
- 用curl模拟http请求获取网页
- 文件操作一些总结
- IP(Internet Protocal) 地址 说明
- c++Primer学习笔记之一:程序的编译与执行
- STOMP协议说明书-1.2版
- HDU 4091Zombie’s Treasure Chest (数学加暴力)
- android手机连接PC无法正常安装驱动
- Android Annotations浅析