Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Janik, Adrianna"'
Autor:
Wicker, Matthew, Sosnin, Philip, Janik, Adrianna, Müller, Mark N., Weller, Adrian, Tsay, Calvin
Proper data stewardship requires that model owners protect the privacy of individuals' data used during training. Whether through anonymization with differential privacy or the use of unlearning in non-anonymized settings, the gold-standard technique
Externí odkaz:
http://arxiv.org/abs/2406.13433
Autor:
Janik, Adrianna, Costabello, Luca
We study the problem of explaining link predictions in the Knowledge Graph Embedding (KGE) models. We propose an example-based approach that exploits the latent space representation of nodes and edges in a knowledge graph to explain predictions. We e
Externí odkaz:
http://arxiv.org/abs/2212.02651
Autor:
Janik, Adrianna, Torrente, Maria, Costabello, Luca, Calvo, Virginia, Walsh, Brian, Camps, Carlos, Mohamed, Sameh K., Ortega, Ana L., Nováček, Vít, Massutí, Bartomeu, Minervini, Pasquale, Campelo, M. Rosario Garcia, del Barco, Edel, Bosch-Barrera, Joaquim, Menasalvas, Ernestina, Timilsina, Mohan, Provencio, Mariano
Background: Stratifying cancer patients according to risk of relapse can personalize their care. In this work, we provide an answer to the following research question: How to utilize machine learning to estimate probability of relapse in early-stage
Externí odkaz:
http://arxiv.org/abs/2211.09856
Autor:
Janik, Adrianna, Sankaran, Kris
The use of remote sensing in humanitarian crisis response missions is well-established and has proven relevant repeatedly. One of the problems is obtaining gold annotations as it is costly and time consuming which makes it almost impossible to fine-t
Externí odkaz:
http://arxiv.org/abs/2202.04766
Autor:
Janik, Adrianna, Sankaran, Kris
Concept discovery is one of the open problems in the interpretability literature that is important for bridging the gap between non-deep learning experts and model end-users. Among current formulations, concepts defines them by as a direction in a le
Externí odkaz:
http://arxiv.org/abs/2202.04753
Cardiac Magnetic Resonance (CMR) is the most effective tool for the assessment and diagnosis of a heart condition, which malfunction is the world's leading cause of death. Software tools leveraging Artificial Intelligence already enhance radiologists
Externí odkaz:
http://arxiv.org/abs/2103.08590
Autor:
Janik, Adrianna
Understanding a black-box model is a major problem in domains that relies on model predictions in critical tasks. If solved, can help to evaluate the trustworthiness of a model. This thesis proposes a user-centric approach to black-box interpretabili
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-269561
Autor:
Buosi, Samuele, Timilsina, Mohan, Janik, Adrianna, Costabello, Luca, Torrente, Maria, Provencio, Mariano, Fey, Dirk, Nováček, Vít
Publikováno v:
In Expert Systems With Applications January 2024 235
Autor:
Timilsina, Mohan, Fey, Dirk, Buosi, Samuele, Janik, Adrianna, Costabello, Luca, Carcereny, Enric, Abreu, Delvys Rodrıguez, Cobo, Manuel, Castro, Rafael López, Bernabé, Reyes, Minervini, Pasquale, Torrente, Maria, Provencio, Mariano, Nováček, Vít
Publikováno v:
In Journal of Biomedical Informatics August 2023 144
Autor:
Anjara, Sabrina G.1 (AUTHOR) sabrina.anjara@accenture.com, Janik, Adrianna2 (AUTHOR), Dunford-Stenger, Amy1 (AUTHOR), Mc Kenzie, Kenneth1 (AUTHOR), Collazo-Lorduy, Ana3 (AUTHOR), Torrente, Maria3 (AUTHOR), Costabello, Luca2 (AUTHOR), Provencio, Mariano3 (AUTHOR)
Publikováno v:
PLoS ONE. 9/14/2023, Vol. 18 Issue 9, p1-21. 21p.