jLSTM / LSTM – “Long Short-Term Memory” for Protein Classification

jLSTM / LSTM

:: DESCRIPTION

jLSTM is the recommended new JAVA-package of “Long Short-Term Memory” for Protein classification (jLSTM_protein). The implementation of the LSTM neural network is the same as in the C package and performs and behaves identically but faster. jLSTM_protein is multithreaded and therefore uses effectively multicore and -processor machines.

Advertisement

LSTM logistic regression / spectrum kernel is a stripped down LSTM which can be interpreted as logistic regression with the spectrum kernel for sequence classification.

::DEVELOPER

Institute of Bioinformatics, Johannes Kepler University Linz

:: SCREENSHOTS

N/A

:: REQUIREMENTS

:: DOWNLOAD

   jLSTM / LSTM

:: MORE INFORMATION

Citation

Sepp Hochreiter, Martin Heusel, and Klaus Obermayer.
“Fast Model-based Protein Homology Detection without Alignment.”
Bioinformatics (2007) 23 (14): 1728-1736..

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.