Galtier MN, Marini C, Wainrib G, Jaeger H. Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes.
Neural Netw 2014;
56:10-21. [PMID:
24815743 DOI:
10.1016/j.neunet.2014.04.002]
[Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2013] [Revised: 04/15/2014] [Accepted: 04/18/2014] [Indexed: 11/30/2022]
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.
Collapse