Find models by
Find models for
Find models of
Unsupervised learning of an efficient short-term memory network (Vertechi, Brendel & Machens 2014)
Download zip file
Help downloading and running models
Learning in recurrent neural networks has been a topic fraught with difficulties and problems. We here report substantial progress in the unsupervised learning of recurrent networks that can keep track of an input signal. Specifically, we show how these networks can learn to efficiently represent their present and past inputs, based on local learning rules only.
Vertechi P, Brendel W, Machens CK (2014) Unsupervised learning of an efficient short-term memory network
Advances in Neural Information Processing Systems
(Click on a link to find other models with that property)
Brendel, Wieland [wieland.brendel at bethgelab.org];
File not selected
<- Select file from this column.