Long short term memory
From Wikipedia, the free encyclopedia
Long short term memory or LSTM is an artificial neural network structure used for time series prediction. Unlike traditional recurrent neural networks, it is capable of doing long term predictions.
[edit] See also
[edit] References
- S. Hochreiter and J. Schmidhuber.. "Neural Computation, 9(8):1735-1780, 1997".
- J. A. Perez-Ortiz et al. "Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets. Neural Networks 16(2):241-250, 2003".
