Deep learning 资料汇总--持续更新

这篇博客主要是把自己了解到的一些深度学习理论及应用方面的资料整合起来,方便以后查阅。

Deep learning 概述

1、Understanding Aesthetics with Deep Learning
https://devblogs.nvidia.com/parallelforall/understanding-aesthetics-deep-learning/

入门

1、UFLDL
http://ufldl.stanford.edu/wiki/index.php/UFLDL教程
2、deep learning with theano
http://deeplearning.net/tutorial/contents.html
中文的http://www.cnblogs.com/charleshuang/p/3651843.html
3、斯坦福机器学习
http://open.163.com/special/opencourse/machinelearning.html

Deep learning 各种框架对比

1、英伟达官方推荐的几个深度学习框架
https://developer.nvidia.com/deep-learning-frameworks?mkt_tok=eyJpIjoiTUdabVlXWmlPRFUwTkdWbSIsInQiOiJzelZwY1dleTVkZWRYemtYZ2JNSExYTHVzMDl3UUlvQ0xpQTZzUVZaXC84Z2NRR2xzZENURmNaTHB2eklJM0V3MWd0UEllSUp4dkg2T1ZXY2R3V3hLUHYzZDdcL0p1SkZqUU9tV2xvRGtBejBBPSJ9
2、博客总结
http://blog.csdn.net/thesby/article/details/51425133

Sequence learning

1、Deep learning in a nutshell

Deep Learning in a Nutshell: Sequence Learning
https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-sequence-learning/

Understanding Natural Language with Deep Neural Networks Using Torch
https://devblogs.nvidia.com/parallelforall/understanding-natural-language-deep-neural-networks-using-torch/

Deep Learning in a Nutshell: Core Concepts
https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-core-concepts/

Deep Speech: Accurate Speech Recognition with GPU-Accelerated Deep Learning
https://devblogs.nvidia.com/parallelforall/deep-speech-accurate-speech-recognition-gpu-accelerated-deep-learning/

2、cuDNN 5对 序列学习的支持
http://geek.csdn.net/news/detail/72705

Relu 的作用

1、Deep Sparse Rectifier Neural Networks
http://machinelearning.wustl.edu/mlpapers/paper_files/AISTATS2011_GlorotBB11.pdf
2、Rectifier Nonlinearities Improve Neural Network Acoustic Models
http://web.stanford.edu/~awni/papers/relu_hybrid_icml2013_final.pdf
3、https://www.douban.com/note/348196265/
4、https://www.quora.com/What-is-special-about-rectifier-neural-units-used-in-NN-learning

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值