Results 1 to 10 of about 27,667 (170)

Interpretability versus Explainability: Classification for Understanding Deep Learning Systems and Models

Computer Assisted Methods in Engineering and Science, 2022
The techniques of explainability and interpretability are not alternatives for many realworld problems, as recent studies often suggest. Interpretable machine learning is not a subset of explainable artificial intelligence or vice versa. While the former
Ivars Namatēvs, Kaspars Sudars, Artis Dobrājs   +2 more
doaj   +1 more source

Novel methods for elucidating modality importance in multimodal electrophysiology classifiers

Frontiers in Neuroinformatics, 2023
IntroductionMultimodal classification is increasingly common in electrophysiology studies. Many studies use deep learning classifiers with raw time-series data, which makes explainability difficult, and has resulted in relatively few studies applying ...
Charles A. Ellis, Charles A. Ellis, Mohammad S. E. Sendi, Mohammad S. E. Sendi, Rongen Zhang, Darwin A. Carbajal, May D. Wang, Robyn L. Miller, Robyn L. Miller, Vince D. Calhoun, Vince D. Calhoun, Vince D. Calhoun   +11 more
doaj   +1 more source

Re-focusing explainability in medicine

Digital Health, 2022
Using artificial intelligence to improve patient care is a cutting-edge methodology, but its implementation in clinical routine has been limited due to significant concerns about understanding its behavior. One major barrier is the explainability dilemma
Laura Arbelaez Ossa, Georg Starke, Giorgia Lorenzini, Julia E Vogt, David M Shaw, Bernice Simone Elger   +5 more
doaj   +1 more source

Explainability for artificial intelligence in healthcare: a multidisciplinary perspective

BMC Medical Informatics and Decision Making, 2020
Background Explainability is one of the most heavily debated topics when it comes to the application of artificial intelligence (AI) in healthcare. Even though AI-driven systems have been shown to outperform humans in certain analytical tasks, the lack ...
Julia Amann, Alessandro Blasimme, Effy Vayena, Dietmar Frey, Vince I. Madai, the Precise4Q consortium   +5 more
doaj   +1 more source

Explainable Distance-Based Outlier Detection in Data Streams

IEEE Access, 2022
Explaining outliers is a topic that attracts a lot of interest; however existing proposals focus on the identification of the relevant dimensions. We extend this rationale for unsupervised distance-based outlier detection, and through investigating ...
Theodoros Toliopoulos, Anastasios Gounaris   +1 more
doaj   +1 more source

Image Embeddings Extracted from CNNs Outperform Other Transfer Learning Approaches in Classification of Chest Radiographs

Diagnostics, 2022
To identify the best transfer learning approach for the identification of the most frequent abnormalities on chest radiographs (CXRs), we used embeddings extracted from pretrained convolutional neural networks (CNNs).
Noemi Gozzi, Edoardo Giacomello, Martina Sollini, Margarita Kirienko, Angela Ammirabile, Pierluca Lanzi, Daniele Loiacono, Arturo Chiti   +7 more
doaj   +1 more source

An Approach to Task Representation Based on Object Features and Affordances

Sensors, 2022
Multi-purpose service robots must execute their tasks reliably in different situations, as well as learn from humans and explain their plans to them.
Paul Gajewski, Bipin Indurkhya
doaj   +1 more source

Machine Learning in Ratemaking, an Application in Commercial Auto Insurance

Risks, 2022
This paper explores the tuning and results of two-part models on rich datasets provided through the Casualty Actuarial Society (CAS). These datasets include bodily injury (BI), property damage (PD) and collision (COLL) coverage, each documenting policy ...
Spencer Matthews, Brian Hartman
doaj   +1 more source

Sequence-Based Explainable Hybrid Song Recommendation

Frontiers in Big Data, 2021
Despite advances in deep learning methods for song recommendation, most existing methods do not take advantage of the sequential nature of song content.
Khalil Damak, Olfa Nasraoui, William Scott Sanders   +2 more
doaj   +1 more source

Generation and evaluation of adaptive explanations based on dynamic partner-modeling and non-stationary decision making

Frontiers in Computer Science
Adapting to the addressee is crucial for successful explanations, yet poses significant challenges for dialog systems. We adopted the approach of treating explanation generation as a non-stationary decision process, in which the optimal strategy varies ...
Amelie S. Robrecht-Hilbig, Amelie S. Robrecht-Hilbig, Christoph Kowalski, Christoph Kowalski, Stefan Kopp, Stefan Kopp   +5 more
doaj   +1 more source