Probabilistic principles for latent space exploration in deep learning

Description of the granted funding

This research project is concerned with combining probabilistic principles with neural network models, in order to improve their interpretability, robustness, and reliability in real-world applications. Probabilistic methods can also help build models that know when they don't know, and are capable of quantifying uncertainties related to their predictions. The project has two parts: The first is related to model building and design by allowing specification of a priori knowledge in the model structure. The second part is related inference and learning in the hidden feature space of the model in applications, where the model exhibits dynamical behaviour.
Show more

Starting year

2021

End year

2026

Granted funding

Arno Solin Orcid -palvelun logo
447 650 €

Related funding decisions

359910
Research costs of Academy Research Fellows(2024)
158 633 €
346600
Research costs of Academy Research Fellows(2021)
240 000 €

Funder

Research Council of Finland

Funding instrument

Academy research fellows

Other information

Funding decision number

339730

Fields of science

Computer and information sciences

Research fields

Tietojenkäsittelytieteet

Identified topics

computer science, information science, algorithms