Title | ||
---|---|---|
Determination of the edge of criticality in echo state networks through Fisher information maximization. |
Abstract | ||
---|---|---|
It is a widely accepted fact that the computational capability of recurrent neural networks (RNNs) is maximized on the so-called “edge of criticality.” Once the network operates in this configuration, it performs efficiently on a specific application both in terms of: 1) low prediction error and 2) high short-term memory capacity. Since the behavior of recurrent networks is strongly influenced by ... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TNNLS.2016.2644268 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | DocType | Volume |
Neurons,Reservoirs,Recurrent neural networks,Training,Learning systems,Jacobian matrices,Probability density function | Journal | 29 |
Issue | ISSN | Citations |
3 | 2162-237X | 10 |
PageRank | References | Authors |
0.54 | 32 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lorenzo Livi | 1 | 304 | 25.67 |
Filippo Maria Bianchi | 2 | 160 | 15.76 |
Cesare Alippi | 3 | 1040 | 115.84 |