Abstract | ||
---|---|---|
We investigate reservoir computing systems whose dynamics are at critical bifurcation points based on center manifold theorem. We take echo state networks as an example and show that the center manifold defines mapping of the input dynamics to higher dimensional space. We also show that the mapping by center manifolds can contribute to recognition of attractors of input dynamics. The implications for realization of reservoir computing as real physical systems are also discussed. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-46687-3_22 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Reservoir computing,Echo state network,Bifurcation phenomena,Center manifold theory,Physical reservoir | Attractor,Topology,Center manifold,Pattern recognition,Computer science,Physical system,Artificial intelligence,Echo state network,Reservoir computing,Manifold,Bifurcation | Conference |
Volume | ISSN | Citations |
9947 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 1 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Toshiyuki Yamane | 1 | 61 | 9.08 |
Seiji Takeda | 2 | 2 | 1.38 |
Daiju Nakano | 3 | 55 | 8.65 |
Gouhei Tanaka | 4 | 51 | 11.80 |
Ryosho Nakane | 5 | 41 | 6.96 |
Shigeru Nakagawa | 6 | 2 | 1.05 |
Akira Hirose | 7 | 426 | 67.35 |