Package lnsc.lstm

Implements Long-Short Term Memory (LSTM) network from the references below with few additional learning schemes.

See:
Description

Class Summary

AbstractLSTMFactory	Basis to write a Long Short-Term Memory (LSMT) network factory.
ETLSTMFactory1	Factory for LSTM network using eligibility traces to find more rapidely association in time space.
ETLSTMMemoryBlock1	LSTM memory block using eligibility traces to find more rapidely association in time space.
ETLSTMNetwork1	LSTM network using eligibility traces to find more rapidely association in time space.
FastLSTMMemoryBlock	Memory blocks for Long Short-Term Memory (LSMT) network.
FastLSTMNetwork	Long Short-Term Memory (LSMT) network.
LSTMDataNames	Title: LSTM
LSTMFactory	Basis to write a Long Short-Term Memory (LSMT) network factory.
OnlineSPMSELearning	Generic Predictive Minimized Sum-squared-error online learning procedure.

Package lnsc.lstm Description

Implements Long-Short Term Memory (LSTM) network from the references below with few additional learning schemes.

Package Specification

• The package requires the LNSC library Build x74 or a higher compatible build.

References

• Gers, Schraudolph, & Schmiduber (2002) Journal of Machine Learning Research 3:115-143.
• Gers, Schmidhuber, & Cummins (2000) Neural Computation 12(10) 2451-2471.
• Hochreiter & Schmidhuber (1997) Neural Computation 9(8):1735-1780).

The code of this library and the conceptual structure of this library are the intellectual property of Francois Rivest. This package was developed for research purpose and any commercial use, and non-educational use is strictly prohibited unless explicit written consent is given by the author Francois Rivest. Copyright 2005-2008.