arXiv Open Access 2014

Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes

Mathieu N. Galtier Camille Marini Gilles Wainrib Herbert Jaeger

Lihat Sumber

Abstrak

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 Nino phenomenon studied in climate research.

Topik & Kata Kunci

nlin.AO

Penulis (4)

Mathieu N. Galtier

Camille Marini

Gilles Wainrib

Herbert Jaeger

Format Sitasi

APA MLA BibTeX

Galtier, M.N., Marini, C., Wainrib, G., Jaeger, H. (2014). Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes. https://arxiv.org/abs/1402.1613

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2014
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓