informed_init
ReservoirComputing.informed_init
— Functioninformed_init([rng], [T], dims...;
scaling=0.1, model_in_size, gamma=0.5)
Create an input layer for informed echo state networks (Pathak et al., 2018).
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 matrix. Should followres_size x in_size
.
Keyword arguments
scaling
: The scaling factor for the input matrix. Default is 0.1.model_in_size
: The size of the input model.gamma
: The gamma value. Default is 0.5.
Examples
References
- Pathak, J.; Wikner, A.; Fussell, R.; Chandra, S.; Hunt, B. R.; Girvan, M. and Ott, E. (2018). Hybrid forecasting of chaotic processes: Using machine learning in conjunction with a knowledge-based model. Chaos: An Interdisciplinary Journal of Nonlinear Science 28.