!!! Overview
[{$pagename}] ([LSTM]) is a [Artificial Neural network] that is a special kind of [Recurrent Neural network], capable of [Machine Learning] long-term dependencies. 

They were introduced by Hochreiter & Schmidhuber ([1997|Year 1997]), and were refined and popularized by many people in following work. 

[{$pagename}]s work tremendously well on a large variety of problems, and are now widely used.

[{$pagename}]s are explicitly designed to avoid the long-term [dependency] problem. Remembering information for long periods of time is practically their default behavior, not something they struggle to learn!

All [Recurrent Neural networks] have the form of a chain of repeating modules of neural network. In standard [RNNs], this repeating module will have a very simple structure, such as a single tanh layer.

!! More Information
There might be more information for this subject on one of the following:
[{ReferringPagesPlugin before='*' after='\n' }]
----
* [#1] - [Long short-term memory|Wikipedia:Long_short-term_memory|target='_blank'] - based on information obtained 2017-04-21-