LSTM-MATLAB-master
所属分类：matlab编程
开发工具：matlab
文件大小：654KB
下载次数：18
上传日期：2020-06-22 16:43:41
上 传 者：
雨哥爱吃瓜
说明： lstm的matlab代码，里面有实际的例子可以参考
(LSTM MATLAB code, there are practical examples to look at)
文件列表:
aStart.m (1053, 2019-11-01)
batch_cell_lstm.m (8858, 2019-11-01)
batch_equal_nomask_lstm.m (8905, 2019-11-01)
clientLoadDataMinibatchNomask_ref.m (1229, 2019-11-01)
data (0, 2019-11-01)
dependence (0, 2019-11-01)
gputype.m (911, 2019-11-01)
Main.m (6659, 2019-11-01)
netInit.m (2859, 2019-11-01)
runClient.m (82, 2019-11-01)
server_batch_cell_lstm.m (178, 2019-11-01)
testmodel.m (7290, 2019-11-01)
data\genadding.m (2527, 2019-11-01)
dependence\computeNumericalGradient.m (1171, 2019-11-01)
dependence\matlabserver_r1 (0, 2019-11-01)
dependence\minFunc_2012 (0, 2019-11-01)
dependence\matlabserver_r1\.svn (0, 2019-11-01)
dependence\matlabserver_r1\@Server (0, 2019-11-01)
dependence\matlabserver_r1\@Slave (0, 2019-11-01)
dependence\matlabserver_r1\addpath_tica.m (749, 2019-11-01)
dependence\matlabserver_r1\dataloader (0, 2019-11-01)
dependence\matlabserver_r1\java2matlab.m (1937, 2019-11-01)
dependence\matlabserver_r1\matlab2java.m (1724, 2019-11-01)
dependence\matlabserver_r1\minFunc (0, 2019-11-01)
dependence\matlabserver_r1\serverRef.m (1759, 2019-11-01)
dependence\matlabserver_r1\setup_paths.m (683, 2019-11-01)
dependence\matlabserver_r1\slaveRandSeed.m (182, 2019-11-01)
dependence\matlabserver_r1\slaveRef.m (1428, 2019-11-01)
dependence\matlabserver_r1\slaveRefDelete.m (361, 2019-11-01)
dependence\matlabserver_r1\slaveRun.m (844, 2019-11-01)
dependence\matlabserver_r1\slaveRun.sh (2034, 2019-11-01)
dependence\matlabserver_r1\softmax (0, 2019-11-01)
dependence\minFunc_2012\autoDif (0, 2019-11-01)
dependence\minFunc_2012\example_derivativeCheck.m (1392, 2019-11-01)
dependence\minFunc_2012\example_minFunc.m (2421, 2019-11-01)
dependence\minFunc_2012\logisticExample (0, 2019-11-01)
... ...
# LSTM-MATLAB
LSTM-MATLAB is Long Short-term Memory (LSTM) in MATLAB, which is meant to be succinct, illustrative and for research purpose only. It is accompanied with a paper for reference: [Revisit Long Short-Term Memory: An Optimization Perspective], NIPS deep learning workshop, 2014.
Creater & Maintainer
Qi Lyu
#FEATURES
- original Long short-term Memory
- all connect peephole
- support optimization methods like LBFGS and CG
- CPU or GPU acceleration
- Mapreduce parallelization
- gradient checking
- easy configuration
- baseline experiment
#ACKNOWLEDGEMENTS
The minFunc code folder included is provided by Mark Schmidt (http://www.cs.ubc.ca/~schmidtm).
MATLAB Mapreduce is provided by Quoc V. Le(http://cs.stanford.edu/~quocle/optimizationWeb/index.html).
#USAGE
To run the code, start from aStart.m. Data is generated by scripts in data directory on-the-fly. For faster LSTM implementation with complete features, see 'LSTMLayer' defined in [C++ version].
The dataset and labels etc follows the original LSTM paper in 1997.
License
----
MIT
[Revisit Long Short-Term Memory: An Optimization Perspective]:http://bigml.cs.tsinghua.edu.cn/~jun/pub/lstm-parallel.pdf
[C++ version]:https://github.com/huashiyiqike/NETLAB/blob/master/layernet/core/layer-inl.hpp
近期下载者：
相关文件：
收藏者：