double_cycle
ReservoirComputing.double_cycle
— Functiondouble_cycle([rng], [T], dims...;
cycle_weight=0.1, second_cycle_weight=0.1,
return_sparse=false)
Creates a double cycle reservoir (Fu et al., 2023).
Arguments
rng
: Random number generator. Default isUtils.default_rng()
from WeightInitializers.T
: Type of the elements in the reservoir matrix. Default isFloat32
.dims
: Dimensions of the reservoir matrix.
Keyword arguments
cycle_weight
: Weight of the upper cycle connections in the reservoir matrix. Default is 0.1.second_cycle_weight
: Weight of the lower cycle connections in the reservoir matrix. Default is 0.1.return_sparse
: flag for returning asparse
matrix. Default isfalse
.
Examples
julia> reservoir_matrix = double_cycle(5, 5; cycle_weight = 0.1, second_cycle_weight = 0.3)
5×5 Matrix{Float32}:
0.0 0.3 0.0 0.0 0.3
0.1 0.0 0.3 0.0 0.0
0.0 0.1 0.0 0.3 0.0
0.0 0.0 0.1 0.0 0.3
0.1 0.0 0.0 0.1 0.0
References
- Fu, J.; Li, G.; Tang, J.; Xia, L.; Wang, L. and Duan, S. (2023). A double-cycle echo state network topology for time series prediction. Chaos: An Interdisciplinary Journal of Nonlinear Science 33.