Abstract | ||
---|---|---|
In this paper, we propose a model of ESNs that eliminates critical dependence on hyper-parameters, resulting in networks that provably cannot enter a chaotic regime and, at the same time, denotes nonlinear behaviour in phase space characterised by a large memory of past inputs, comparable to the one of linear networks. Our contribution is supported by experiments corroborating our theoretical findings, showing that the proposed model displays dynamics that are rich-enough to approximate many common nonlinear systems used for benchmarking. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-30493-5_9 | ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: WORKSHOP AND SPECIAL SESSIONS |
Keywords | Field | DocType |
Echo State Networks, Edge of criticality, Memory-nonlinearity tradeoff | Nonlinear system,Pattern recognition,Computer science,Phase space,Algorithm,Artificial intelligence,Chaotic,Benchmarking | Conference |
Volume | ISSN | Citations |
11731 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pietro Verzelli | 1 | 1 | 1.71 |
Cesare Alippi | 2 | 1040 | 115.84 |
Lorenzo Livi | 3 | 304 | 25.67 |