LSTM-MATLAB-master

所属分类:数值算法/人工智能
开发工具:matlab
文件大小:493KB
下载次数:215
上传日期:2017-11-22 17:03:05
上 传 者robinio11
说明:  LSTM作为经典的回归神经网络类型,可以用于实现时序数据的预测。
(It is used for prediction of time series data)

文件列表:
aStart.m (1053, 2015-12-28)
batch_cell_lstm.m (8858, 2015-12-28)
batch_equal_nomask_lstm.m (8905, 2015-12-28)
clientLoadDataMinibatchNomask_ref.m (1229, 2015-12-28)
coefficient_determination.m (217, 2016-09-21)
data\genadding.m (2527, 2015-12-28)
dependence\computeNumericalGradient.m (1171, 2015-12-28)
dependence\matlabserver_r1\.svn\entries (2022, 2015-12-28)
dependence\matlabserver_r1\.svn\prop-base\slaveRun.sh.svn-base (30, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\addpath_tica.m.svn-base (749, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\java2matlab.m.svn-base (1937, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\matlab2java.m.svn-base (1724, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\serverRef.m.svn-base (1759, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\setup_paths.m.svn-base (838, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\slaveRandSeed.m.svn-base (182, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\slaveRef.m.svn-base (1428, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\slaveRefDelete.m.svn-base (361, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\slaveRun.m.svn-base (666, 2015-12-28)
dependence\matlabserver_r1\.svn\text-base\slaveRun.sh.svn-base (2037, 2015-12-28)
dependence\matlabserver_r1\@Server\.svn\entries (1176, 2015-12-28)
dependence\matlabserver_r1\@Server\.svn\text-base\emulateSlaveProcessRequest.m.svn-base (982, 2015-12-28)
dependence\matlabserver_r1\@Server\.svn\text-base\getReply.m.svn-base (1090, 2015-12-28)
dependence\matlabserver_r1\@Server\.svn\text-base\rpc.m.svn-base (3504, 2015-12-28)
dependence\matlabserver_r1\@Server\.svn\text-base\rpcsum.m.svn-base (560, 2015-12-28)
dependence\matlabserver_r1\@Server\.svn\text-base\sendRequest.m.svn-base (672, 2015-12-28)
dependence\matlabserver_r1\@Server\.svn\text-base\Server.m.svn-base (7443, 2015-12-28)
dependence\matlabserver_r1\@Server\emulateSlaveProcessRequest.m (982, 2015-12-28)
dependence\matlabserver_r1\@Server\getReply.m (1090, 2015-12-28)
dependence\matlabserver_r1\@Server\rpc.m (3504, 2015-12-28)
dependence\matlabserver_r1\@Server\rpcsum.m (560, 2015-12-28)
dependence\matlabserver_r1\@Server\sendRequest.m (672, 2015-12-28)
dependence\matlabserver_r1\@Server\Server.m (7443, 2015-12-28)
dependence\matlabserver_r1\@Slave\.svn\entries (1013, 2015-12-28)
dependence\matlabserver_r1\@Slave\.svn\text-base\getRequest.m.svn-base (488, 2015-12-28)
dependence\matlabserver_r1\@Slave\.svn\text-base\hook.m.svn-base (1213, 2015-12-28)
dependence\matlabserver_r1\@Slave\.svn\text-base\processRequest.m.svn-base (2284, 2015-12-28)
dependence\matlabserver_r1\@Slave\.svn\text-base\sendReply.m.svn-base (284, 2015-12-28)
dependence\matlabserver_r1\@Slave\.svn\text-base\Slave.m.svn-base (1372, 2015-12-28)
dependence\matlabserver_r1\@Slave\getRequest.m (488, 2015-12-28)
... ...

# 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