Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes.
other · Level V
Where this comes from
- Record sourced from PubMed, PMID 24815743.
- Also identified by DOI 10.1016/j.neunet.2014.04.002.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
A method is provided for designing and training noise-driven recurrent neural networks as models of stochastic processes. The method unifies and generalizes two known separate modeling approaches, Echo State Networks (ESN) and Linear Inverse Modeling (LIM), under the common principle of relative entropy minimization. The power of the new method is demonstrated on a stochastic approximation of the El Niño phenomenon studied in climate research.
Medical subject headings
- Entropy
- Neural Networks, Computer
- Nonlinear Dynamics
- Stochastic Processes