Long short-term memory
S Hochreiter, J Schmidhuber - Neural computation, 1997 - ieeexplore.ieee.org
Learning to store information over extended time intervals by recurrent backpropagation takes
a very long time, mostly because of insufficient, decaying error backflow. We briefly review …
a very long time, mostly because of insufficient, decaying error backflow. We briefly review …
[PDF][PDF] Long short-term memory
J Schmidhuber, S Hochreiter - Neural Comput, 1997 - people.idsia.ch
… long time lag recurrent net project, since 2002 assistant professor in Berlin) … LSTM: 1
input unit, 1 input at a time (memory overhead) … • LSTM may offer a better solution by …
input unit, 1 input at a time (memory overhead) … • LSTM may offer a better solution by …
[PDF][PDF] Bridging long time lags by weight guessing and “Long Short-Term Memory”
S Hochreiter, J Schmidhuber - … models in biological and artificial systems, 1996 - bioinf.jku.at
… We then use long short term memory (LSTM), our own recent algorithm, to solve hard problems
that can neither be quickly solved by random weight guessing nor by any other recurrent …
that can neither be quickly solved by random weight guessing nor by any other recurrent …
Lipreading with long short-term memory
…, J Koutník, J Schmidhuber - 2016 IEEE International …, 2016 - ieeexplore.ieee.org
… Feedforward and recurrent neural network layers (namely Long Short-Term Memory; LSTM)
are stacked to form a single structure which is trained by back-propagating error gradients …
are stacked to form a single structure which is trained by back-propagating error gradients …
Long short-term memory learns context free and context sensitive languages
FA Gers, J Schmidhuber - Artificial Neural Nets and Genetic Algorithms …, 2001 - Springer
Previous work on learning regular languages from exemplary training sequences showed
that Long Short- Term Memory (LSTM) outperforms traditional recurrent neural networks (…
that Long Short- Term Memory (LSTM) outperforms traditional recurrent neural networks (…
Learning to forget: Continual prediction with LSTM
… In this article, however, we show that even LSTM fails to learn to process certain very long
… to span long time lags must also address the issue of forgetting in short-term memory (unit …
… to span long time lags must also address the issue of forgetting in short-term memory (unit …
[PDF][PDF] A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks
… The approach uses a bidirectional recurrent neural network with long short-term memory
blocks. We use a recently introduced objective function, known as Connectionist Temporal …
blocks. We use a recently introduced objective function, known as Connectionist Temporal …
Recurrent nets that time and count
FA Gers, J Schmidhuber - Proceedings of the IEEE-INNS …, 2000 - ieeexplore.ieee.org
… We focus on Long Short-Term Memory (LSTM) because it usually outperforms other
RNNs. Surprisingly, LSTM augmented by “peephole connections” from its internal cells to its …
RNNs. Surprisingly, LSTM augmented by “peephole connections” from its internal cells to its …
[HTML][HTML] Deep learning
J Schmidhuber - Scholarpedia, 2015 - scholarpedia.org
… RNNs, the deepest of all NNs, may learn to solve problems of potentially unlimited depth,
for example, by learning to store in their activation-based "short-term memory" representations …
for example, by learning to store in their activation-based "short-term memory" representations …
Training recurrent networks by evolino
… 2.2 Long Short-Term Memory. LSTM is a recurrent neural network purposely designed to
learn long-… The unique feature of the LSTM architecture is the memory cell, which is capable of …
learn long-… The unique feature of the LSTM architecture is the memory cell, which is capable of …