TY  - JOUR
U1  - Wissenschaftlicher Artikel
A1  - Herzog, Bodo
T1  - Fractional stochastic search algorithms: modelling complex systems via AI
JF  - Mathematics
N2  - The aim of this article is to establish a stochastic search algorithm for neural networks based on the fractional stochastic processes {𝐵𝐻𝑡,𝑡≥0} with the Hurst parameter 𝐻∈(0,1). We define and discuss the properties of fractional stochastic processes, {𝐵𝐻𝑡,𝑡≥0}, which generalize a standard Brownian motion. Fractional stochastic processes capture useful yet different properties in order to simulate real-world phenomena. This approach provides new insights to stochastic gradient descent (SGD) algorithms in machine learning. We exhibit convergence properties for fractional stochastic processes.
Y1  - 2023
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:rt2-opus4-46131
U6  - https://doi.org/10.3390/math11092061
DO  - https://doi.org/10.3390/math11092061
VL  - 11
IS  - 9
SP  - 1
EP  - 11
S1  - 11
PB  - MDPI
CY  - Basel
ER  -