He has been working at EDI since 2020. His research interests focus on supervised and unsupervised machine learning, specifically the Joint Embedding Predictive Architecture (JEPA) for building global models, as well as the study of latent space geometry, decoupling, and dynamics using deep neural networks and explainable artificial intelligence, primarily in medical imaging.
Author and co-author of more than twenty SCOPUS-indexed scientific publications, not only in the field of medicine but also in research related to agriculture, construction, smart energy, and privacy protection.
Recent projects
-
A Deep Learning Approach for Osteoporosis Identification using Cone-beam Computed Tomography (OSTAK)
-
“Applied Research” Component 2 in the areas of ICT and Smart Energy – LACISE
-
New technology to produce hydrogen from Renewable Energy Sources based on AI with optimized costs for environmental applications (HydroG(re)EnergY-Env)
-
Digitalization of Power Electronic Applications within Key Technology Value Chains (PowerizeD) #ChipsJU
-
Long-term State Research Program «Research platform for innovative products in biomedicine and photonics» (BioPhoT) #SRP (VPP)
Recent publications
- Sudars, Kaspars, Ivars Namatēvs, and Kaspars Ozols. 2022. "Improving Performance of the PRYSTINE Traffic Sign Classification by Using a Perturbation-Based Explainability Approach" Journal of Imaging 8, no. 2: 30. https://doi.org/10.3390/jimaging8020030
- Arturs Nikulins, Kaspars Sudars, Edgars Edelmers, Ivars Namatevs, Kaspars Ozols, Vitalijs Komasilovs, Aleksejs Zacepins, Armands Kviesis, Andreas Reinhardt. "Deep Learning for Wind and Solar Energy Forecasting in Hydrogen Production" Energies 17(5): pp.12. https://www.mdpi.com/1996-1073/17/5/1053
- Anda Slaidina, Laura Neimane, Oskars Radzins, Ivars Namatevs, Kaspars Sudars "E-Poster: The effect of osteoporosis on the bone quantity and quality of the edentulous mandible" Clinical Oral Implants Research
- Ivars Namatevs, Kaspars Sudars, Arturs Nikulins, Kaspars Ozols. 2025. "Privacy Auditing in Differential Private Machine Learning: The Current Trends" Applied Sciences, 15(2): 647. https://doi.org/10.3390/app15020647
- Sudars, K., Namatevs, I., Nikulins, A., & Ozols, K. (2025). Privacy Auditing of Lithium-Ion Battery Ageing Model by Recovering Time-Series Data Using Gradient Inversion Attack in Federated Learning. Applied Sciences, 15(10), 5704.