Learning minimal representations of stochastic processes with variational autoencoders

doi:doi:10.57702/2jc04dta

Learning minimal representations of stochastic processes with variational autoencoders

Stochastic processes have found numerous applications in science, as they are broadly used to model a variety of natural phenomena. The dataset consists of trajectories of stochastic processes, including Brownian motion, fractional Brownian motion, and scaled Brownian motion.

BibTex:

@dataset{Gabriel_Fernández-Fernández_and_Carlo_Manzo_and_Maciej_Lewenstein_and_Alexandre_Dauphin_and_Gorka_Muñoz-Gil_2024,
    abstract = {Stochastic processes have found numerous applications in science, as they are broadly used to model a variety of natural phenomena. The dataset consists of trajectories of stochastic processes, including Brownian motion, fractional Brownian motion, and scaled Brownian motion.},
    author = {Gabriel Fernández-Fernández and Carlo Manzo and Maciej Lewenstein and Alexandre Dauphin and Gorka Muñoz-Gil},
    doi = {10.57702/2jc04dta},
    institution = {No Organization},
    keyword = {'Anomalous Diffusion', 'Diffusion Processes', 'Stochastic Processes', 'Variational Autoencoders'},
    month = {dec},
    publisher = {TIB},
    title = {Learning minimal representations of stochastic processes with variational autoencoders},
    url = {https://service.tib.eu/ldmservice/dataset/learning-minimal-representations-of-stochastic-processes-with-variational-autoencoders},
    year = {2024}
}