Leveraging explanations in interactive machine learning: An overview
Explanations have gained an increasing level of interest in the AI and Machine Learning
(ML) communities in order to improve model transparency and allow users to form a mental …
(ML) communities in order to improve model transparency and allow users to form a mental …
[HTML][HTML] Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions
Understanding black box models has become paramount as systems based on opaque
Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response …
Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response …
Pip-net: Patch-based intuitive prototypes for interpretable image classification
M Nauta, J Schlötterer… - Proceedings of the …, 2023 - openaccess.thecvf.com
Interpretable methods based on prototypical patches recognize various components in an
image in order to explain their reasoning to humans. However, existing prototype-based …
image in order to explain their reasoning to humans. However, existing prototype-based …
Interpretable image classification with differentiable prototypes assignment
D Rymarczyk, Ł Struski, M Górszczak… - … on Computer Vision, 2022 - Springer
Existing prototypical-based models address the black-box nature of deep learning.
However, they are sub-optimal as they often assume separate prototypes for each class …
However, they are sub-optimal as they often assume separate prototypes for each class …
Explainable image classification: The journey so far and the road ahead
V Kamakshi, NC Krishnan - AI, 2023 - mdpi.com
Explainable Artificial Intelligence (XAI) has emerged as a crucial research area to address
the interpretability challenges posed by complex machine learning models. In this survey …
the interpretability challenges posed by complex machine learning models. In this survey …
Glancenets: Interpretable, leak-proof concept-based models
E Marconato, A Passerini… - Advances in Neural …, 2022 - proceedings.neurips.cc
There is growing interest in concept-based models (CBMs) that combine high-performance
and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. A …
and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. A …
This looks like those: Illuminating prototypical concepts using multiple visualizations
We present ProtoConcepts, a method for interpretable image classification combining deep
learning and case-based reasoning using prototypical parts. Existing work in prototype …
learning and case-based reasoning using prototypical parts. Existing work in prototype …
Icicle: Interpretable class incremental continual learning
D Rymarczyk, J van de Weijer… - Proceedings of the …, 2023 - openaccess.thecvf.com
Continual learning enables incremental learning of new tasks without forgetting those
previously learned, resulting in positive knowledge transfer that can enhance performance …
previously learned, resulting in positive knowledge transfer that can enhance performance …
Protovae: A trustworthy self-explainable prototypical variational model
The need for interpretable models has fostered the development of self-explainable
classifiers. Prior approaches are either based on multi-stage optimization schemes …
classifiers. Prior approaches are either based on multi-stage optimization schemes …
Towards interpretable deep reinforcement learning with human-friendly prototypes
Despite recent success of deep learning models in research settings, their application in
sensitive domains remains limited because of their opaque decision-making processes …
sensitive domains remains limited because of their opaque decision-making processes …