Zobrazeno 1 - 10
of 228
pro vyhledávání: '"Främling, Kary"'
Local explanation of machine learning (ML) models has recently received significant attention due to its ability to reduce ambiguities about why the models make specific decisions. Extensive efforts have been invested to address explainability for di
Externí odkaz:
http://arxiv.org/abs/2410.12996
Autor:
Khajavi, Siavash H., Moshtaghi, Mehdi, Yu, Dikai, Liu, Zixuan, Främling, Kary, Holmström, Jan
The fuzzy object detection is a challenging field of research in computer vision (CV). Distinguishing between fuzzy and non-fuzzy object detection in CV is important. Fuzzy objects such as fire, smoke, mist, and steam present significantly greater co
Externí odkaz:
http://arxiv.org/abs/2410.01124
Autor:
Pihlgren, Gustav Grund, Främling, Kary
Perturbation-based post-hoc image explanation methods are commonly used to explain image prediction models by perturbing parts of the input to measure how those parts affect the output. Due to the intractability of perturbing each pixel individually,
Externí odkaz:
http://arxiv.org/abs/2409.04116
Autor:
Främling, Kary
The availability of easy-to-use and reliable software implementations is important for allowing researchers in academia and industry to test, assess and take into use eXplainable AI (XAI) methods. This paper describes the \texttt{py-ciu} Python imple
Externí odkaz:
http://arxiv.org/abs/2408.09957
Autor:
Främling, Kary
When used in the context of decision theory, feature importance expresses how much changing the value of a feature can change the model outcome (or the utility of the outcome), compared to other features. Feature importance should not be confused wit
Externí odkaz:
http://arxiv.org/abs/2308.03589
Autor:
Patil, Minal Suresh, Främling, Kary
Contextual utility theory integrates context-sensitive factors into utility-based decision-making models. It stresses the importance of understanding individual decision-makers' preferences, values, and beliefs and the situational factors that affect
Externí odkaz:
http://arxiv.org/abs/2303.13552
Autor:
Patil, Minal Suresh, Främling, Kary
This work introduces the notion of intermediate concepts based on levels structure to aid explainability for black-box models. The levels structure is a hierarchical structure in which each level corresponds to features of a dataset (i.e., a player-s
Externí odkaz:
http://arxiv.org/abs/2303.11920
Autor:
Främling, Kary
This paper provides new theory to support to the eXplainable AI (XAI) method Contextual Importance and Utility (CIU). CIU arithmetic is based on the concepts of Multi-Attribute Utility Theory, which gives CIU a solid theoretical foundation. The novel
Externí odkaz:
http://arxiv.org/abs/2202.07292
Publikováno v:
Applied Soft Computing July 2021
A key aspect for the forklifts is the state-of-health (SoH) assessment to ensure the safety and the reliability of uninterrupted power source. Forecasting the battery SoH well is imperative to enable preventive maintenance and hence to reduce the cos
Externí odkaz:
http://arxiv.org/abs/2107.05489
In the present paper we present the potential of Explainable Artificial Intelligence methods for decision-support in medical image analysis scenarios. With three types of explainable methods applied to the same medical image data set our aim was to i
Externí odkaz:
http://arxiv.org/abs/2105.02357