DL论文笔记 | Wei Zhu's DL Station
分类 DL论文笔记 下的文章
[转载]深度学习论文之Do Deep Nets Really Need to be Deep?

View more

[转载]深度学习论文之Do Deep Nets Really Need to be Deep?

今天我们要谈论的文章为: Lei Jimmy Ba, and Rich Caurana. Do Deep Nets Really Need to be Deep?. ICLR2014 openreview中有下载链接和讨论: http://openreview.net/document/9a7247d9-d18e-4549-a10c-ca315d84b6db#9a...
[转载]深度学习论文之Big Neural Networks Waste Capacity

View more

[转载]深度学习论文之Big Neural Networks Waste Capacity

本文转自:http://blog.csdn.net/chenli2010/article/details/24290623 本文我们要谈论的文章为: Yann N. Dauphin, Yoshua Bengio. Big Neural Networks Waste Capacity. ICLR2013. 文章下载地址:http://ar...
[转载]深度学习论文笔记:OverFeat

View more

[转载]深度学习论文笔记:OverFeat

原文转自:http://blog.csdn.net/chenli2010/article/details/25204241 今天我们要谈论的文章为: OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. ICLR2014. 这是...
1998_Efficient Backprop

View more

1998_Efficient Backprop

看了神经网络许久,开始自己训练一些网络,用的只是deeplearning toolbox中的一些样例,发现在实际过程中,训练网络达到最优解需要很多的tricks,实际上神经网络的调参比理论更难,记得某篇文章中说过,调参实际上more than the art of theory,这篇文章是1998年Yann LeCun的应用文章,讲解了许多调参经验,对初学者帮助很大。

Deep big simple neural nets excel on hand-written digit recognition

View more

Deep big simple neural nets excel on hand-written digit recognition

2010_Deep big simple neural nets excel on hand-written digit recognition 首先看这篇文章: 2003_Best practice for convolutional neural networks applied to visual document analysis ...
An analysis of single-layer network in unsupervised feature learning

View more

An analysis of single-layer network in unsupervised feature learning

此文详细研究了单层网络的几个因素,分析很到位,对初学者帮助较大。

What is the best multi-stage architecture for Object Recognition?

View more

What is the best multi-stage architecture for Object Recognition?

个人认为这是一篇很好的分析型文章,思路浅显易懂,实验验证也很充分。

SDBN-Sparse deep belief net model for visual area V2

View more

SDBN-Sparse deep belief net model for visual area V2

NIPS_2007_Sparse deep belief net model for visual area V2 这篇文章主要讲的是sparse DBN。很多比较学习算法的结果与V1区域相似的工作,但是没有与大脑视觉体系更深层次的比较,比如...
2010_Tutorial_Feature Learning for Image Classification笔记

View more

2010_Tutorial_Feature Learning for Image Classification笔记

这篇ECCV2010上的tutorial,由余凯和Andrew Ng两位大神做的,我在此把ppt中一些摘要整理一下,供大家参考。

SRBM-Modeling image patches with a directed hierarchy of MRF

View more

SRBM-Modeling image patches with a directed hierarchy of MRF

这篇文章主要介绍了Semi-RBM,也就是半受限玻尔兹曼机,在RBM中加入可视层单元之间的连接,并且使用mean-field approximation。