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.
1 . Vertechi P, Brendel W, Machens CK (2014) Unsupervised learning of an efficient short-term memory network Advances in Neural Information Processing Systems 27:1-9
Model Information (Click on a link to find other models with that property)
Model Type: Connectionist Network;
Brain Region(s)/Organism:
Cell Type(s):
Gap Junctions:
Simulation Environment: Python;
Model Concept(s):
Implementer(s): Brendel, Wieland [wieland.brendel at bethgelab.org];
File not selected

<- Select file from this column.
Loading data, please wait...