huashiyiqike/LSTM-MATLAB

Version 1.1.0.0 (612 KB) von Qi Lyu
LSTM_MATLAB is meant to be succinct, illustrative and for research purpose only.
1,6K Downloads
Aktualisiert 13. Dez 2020

# 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.
#Features
- original Long short-term Memory
- all connect peephole
- 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).

License
----
MIT

[Revisit Long Short-Term Memory: An Optimization Perspective]:http://bigml.cs.tsinghua.edu.cn/~jun/pub/lstm-parallel.pdf

Zitieren als

Qi Lyu (2024). huashiyiqike/LSTM-MATLAB (https://github.com/huashiyiqike/LSTM-MATLAB), GitHub. Abgerufen .

Kompatibilität der MATLAB-Version
Erstellt mit R2011a
Kompatibel mit allen Versionen
Plattform-Kompatibilität
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

data

dependence

dependence/matlabserver_r1

dependence/matlabserver_r1/@Server

dependence/matlabserver_r1/@Slave

dependence/matlabserver_r1/dataloader

dependence/matlabserver_r1/dataloader/tiny

dependence/matlabserver_r1/minFunc

dependence/matlabserver_r1/minFunc/logistic

dependence/matlabserver_r1/softmax

dependence/minFunc_2012

dependence/minFunc_2012/autoDif

dependence/minFunc_2012/logisticExample

dependence/minFunc_2012/minFunc

Versionen, die den GitHub-Standardzweig verwenden, können nicht heruntergeladen werden

Version Veröffentlicht Versionshinweise
1.1.0.0

GITHUB Title

Um Probleme in diesem GitHub Add-On anzuzeigen oder zu melden, besuchen Sie das GitHub Repository.
Um Probleme in diesem GitHub Add-On anzuzeigen oder zu melden, besuchen Sie das GitHub Repository.