Projects per year
Abstract
We review generalized additive models as a type of ‘transparent’ model that has recently seen renewed interest in the deep learning community as neural additive models. We highlight multiple types of nonidentifiability in this model class and discuss challenges in interpretability, arguing for restraint when claiming ‘interpretability’ or ‘suitability for safety-critical applications’ of such models.
| Original language | English |
|---|---|
| Publication status | Published - 2024 |
| MoE publication type | Not Eligible |
| Event | Workshop on Explainable Artificial Intelligence - Virtual, Online Duration: 14 Aug 2024 → 15 Aug 2024 https://sites.google.com/view/xai2024/ |
Workshop
| Workshop | Workshop on Explainable Artificial Intelligence |
|---|---|
| Abbreviated title | XAI |
| City | Virtual, Online |
| Period | 14/08/2024 → 15/08/2024 |
| Internet address |
Fingerprint
Dive into the research topics of 'Challenges in interpretability of additive models'. Together they form a unique fingerprint.Projects
- 3 Finished
-
HEALED/Kaski S.: Human-steered next-generation machine learning for reviving drug design (HEALED)
Kaski, S. (Principal investigator), Masood, A. (Project Member), Stefanović, O. (Project Member), Zhang, X. (Project Member), Naumov, A. (Project Member), Barabanshchikova, P. (Project Member), Soumi, R. (Project Member), Guo, Y. (Project Member), Nguyen, B. (Project Member), Nahal, Y. (Project Member), Zhu, L. (Project Member) & Martinelli, J. (Project Member)
01/09/2021 → 31/08/2025
Project: RCF Academy Project
-
ELISE: European Learning and Intelligent Systems Excellence
Kaski, S. (Principal investigator), Heinäsmäki, S. (Project Member) & Ylöstalo, T. (Project Member)
01/09/2020 → 31/08/2024
Project: EU H2020 Framework program
-
-: Finnish Center for Artificial Intelligence
Kaski, S. (Principal investigator)
01/01/2019 → 31/12/2022
Project: Academy of Finland: Other research funding