Project detail

Interpretable Sparse Artificial Neural Networks – for Spectroscopic Data

Duration: 01.03.2023 — 28.02.2024

Funding resources

Brno University of Technology - Vnitřní projekty VUT

- whole funder (2023-01-01 - 2024-12-31)

On the project

Artificial neural networks (not only) in spectroscopy suffer from poor interpretability due to an extensive number of parameters in the model. We propose an entirely new perspective on interpretability through lottery tickets (i.e., tiny, sparse networks with high performance). We will exploit lottery tickets for interpretability as they dramatically reduce the number of parameters and preserve the spatial structure of the data. Also, we will study a potential of lottery tickets for embedded spectroscopic systems (e.g., satellites, rovers).

Mark

CEITEC VUT-J-23-8332

Default language

Czech

People responsible

Pořízka Pavel, doc. Ing., Ph.D. - fellow researcher
Vrábel Jakub, Ing. - principal person responsible

Units

Advanced instrumentation and methods for material characterization
- (2023-01-01 - 2023-12-31)
Central European Institute of Technology BUT
- (2023-01-29 - 2023-03-06)

Responsibility: Vrábel Jakub, Ing.