Recurrent Neural Network 学习之路

Recurrent Neural Network 学习之路

Followed by distinctive figures in corresponding articles.

1. Read paper: "A critical review of Recurrent Neural Networks for Sequence Learning".


2. Read blog: LSTM简介以及数学推导(FULL BPTT)


3. Read blog: Recurrent Neural Networks Tutorial, Part 1 – Introduction to RNNs


Another way to build deep Recurrent Neural Networks:Generating Sequences with Recurrent Neural Networks



4. Read blog:The unreasonable effectiveness of Recurrent Neural Network - Andrej Karpathy blog





5. Read blog:Understanding LSTM Networks (Nice post series)



6. Read the important paper: "Supervised Sequence Labelling with Recurrent Neural Networks" - Alex Graves

 

7. Read the special tutorial from Schmidhuber (IDSIA):

http://people.idsia.ch/~juergen/lstm/sld001.htm


8. Take a note for this paper: A clockwork RNN


9. read a paper about early stopping for training: Early stopping-but when?

10. keep in touch with the work from DeepMind: https://deepmind.com/publications.html


Code learning:

1. blog: http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/

2. Andrej Karpathy:

Minimal character-level language model with a Vanilla Recurrent Neural Network

3. code from uyaseen. It's proved to be runable.

https://github.com/uyaseen/theano-recurrence





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