【文献阅读】Augmenting Supervised Neural Networks with Unsupervised Objectives-ICML-2016
一、Abstract
从近期对unsupervised learning 的研究得到启发,在large-scale setting 上,本文把unsupervised learning 与supervised learning结合起来,提高了supervised learning的性能。主要是把autoencoder与CNN结合起来
二、Key words:
SAE;SWWAE; reconstruction;encoder;decoder;VGG-16;Alex-Net
三、 Motivation
- reconstruction loss 很有用,reconstruction loss可以看作一个regularizer(SWWAE文中提到).
- unsupervised learning会对model起一定的限定作用,即相当于一个regularizer,这个regularizer使得encoder阶段提取得到的特征具有可解释性
四、Main contributions
- 本文实验表明了,high-capacity neural networks(采用了known switches)的 intermediate activations 可以保存input的大量信息,除了部分
2.通过结合decoder pathway 的loss,提升了supervised learning model的分类正确率
3.做了几个 autoencoder模型的对比实验,发现: the pooling switches and the layer-wise reconstruction loss 非常重要!
五、Inspired by
- Zhao, J., Mathieu, M., Goroshin, R., and Lecun, Y. Stacked what-where auto-encoders. ArXiv:1506.02351, 2015.
- Simonyan, K. and Zisserman, A. Very deep convolutional networks for large-scale image recognition. In ICLR,2015.
- Krizhevsky, A., Sutskever, I., and Hinton, G. E. Imagenet classification with deep convolutional neural networks.In NIPS, 2012.
Rasmus, A., Valpola, H., Honkala, M., Berglund, M., and Raiko, T. Semi-supervised learning with ladder network.In NIPS, 2015. - Adaptive deconvolutional networks for mid and high level feature learning
- Zeiler, M. D., Krishnan, D., Taylor, G. W., and Fergus, R. Deconvolutional networks. CVPR, 2010.
- Zeiler, M., Taylor, G., and Fergus, R. Adaptive deconvolu-tional networks for mid and high level feature learning.In ICCV, 2011.
key word:SWWAE;VGG-16;Alex-Net;ladder-Net;Deconvolutional network
六、文献具体实验及结果
1.SAE-all模型的训练:
第一步,采用VGG-16(训练好的VGG-16)初始化encoder,采用gaussian初始化decoder
第二步,固定encoder部分,用layerwise的方法训练decoder
第三步,用数据整体的训练更新decoder和encoder的参数
SAE-first模型的训练同SAE-all
SAE-layerwise一般只是拿来初始化 SAE-first SAE-all
SWWAE-all 提升了 1.66 % and 1.18% for single-crop and convolution schemes.
(top-1)
七、 感悟
- 2006~2010年期间, unsupervised learning 盛行是以为当时有标签数据不够大,所以需要用unsupervised leanring 的方法来初始化网络,可以取得较好效果,而 类似imagenet这样的大量标签数据的出现, 用autoencoder来初始化网络的优势已经没有。从这里也可以知道,当数据量较小时,可以考虑用unsupervised learning 的方法来初始化网络,从而提升分类准确率
- reconstruction loss 可以看作 regularization , 即是对enconder的weights做了一些限制,限制其获得的activations要能recon出input,是的提取得到的特征具有可解释性
【文献阅读】Augmenting Supervised Neural Networks with Unsupervised Objectives-ICML-2016相关推荐
- 文献阅读:Improving neural networks by preventing co-adaptation of feature detectors
文献阅读:Improving neural networks by preventing co-adaptation of feature detectors ----通过防止特征检测器的共适应以改进 ...
- 【文献阅读】Self-Normalizing Neural Networks
Self-Normalizing Neural Networks ,长达93页的附录足以成为吸睛的地方(给人感觉很厉害), 此paper提出了新的激活函数,称之为 SELUs ,其具有normaliz ...
- [文献阅读]A deep neural network for unsupervised anomaly detection and diagnosis in MTSD
A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series D ...
- 文献阅读:SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples
文献阅读:SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples 1. 内 ...
- 论文阅读2018-Deep Convolutional Neural Networks for breast cancer screening 重点:利用迁移学习三个网络常规化进行分类
论文阅读2018-Deep Convolutional Neural Networks for breast cancer screening 摘要:我们探讨了迁移学习的重要性,并通过实验确定了在训练 ...
- [论文阅读笔记]Deep Neural Networks are Easily Fooled:High Confidence Predictions for Unrecognizable Images
Deep Neural Networks are Easily Fooled:High Confidence Predictions for Unrecognizable Images(CVPR201 ...
- 【论文阅读】Deep Neural Networks for Learning Graph Representations | day14,15
<Deep Neural Networks for Learning Graph Representations>- (AAAI-16)-2016 文章目录 一.模型 1.1解决了两个问题 ...
- 论文阅读:Recurrent Neural Networks for Time Series Forecasting Current Status and Future Directions
typora-copy-images-to: ./ Recurrent Neural Networks for Time Series Forecasting: Current Status and ...
- 论文阅读:Convolutional Neural Networks for Sentence Classification 卷积神经网络的句子分类
Convolutional Neural Networks for Sentence Classification 卷积神经网络的句子分类 目录 Convolutional Neural Networ ...
最新文章
- Java 专业人士必备的书籍和网站列表
- 【算法学习笔记】43.动态规划 逆向思维 SJTU OJ 1012 增长率问题
- djanjo 使用a标签跳转_django页面跳转怎么写
- 大数据工作流_大数据和人工智能时代下的数字化工作流
- 织梦文章添加字段填栏目id,内容页调用字段里的栏目文章
- (待定系数法)A/B
- C/C++网络编程工作笔记0004---socket()函数详解
- Neutron的SDN化
- 2016 网易校招内推C/C++第二场8.6
- 【VMware vSAN 7.0】5.4.2 创建 vSAN 集群—我们有软硬件解决方案
- 【无标题】红外人脸数据集
- 为什么要用用例图 用例图是什么 用例图怎么画 用例图有哪些元素
- [笑话]让古龙看了要痛哭的高考作文(作品相当强,但得了零分,据说被破格入取了)!!!...
- UWB技术的工作原理
- CentOS利用WebHook实现PHP自动部署Git代码
- 获取股票历史数据——数据采集(1)
- [句子成分] 四、状语 定语 同位语
- Spring源码分析系列——bean创建过程分析(三)——工厂方法创建bean
- 天龙 - Terrain
- 领域驱动设计(DDD)