Deep learning for detecting and locating myocardial infarction by electrocardiogram: A literature review
P Xiong, SMY Lee, G Chan - Frontiers in cardiovascular medicine, 2022 - frontiersin.org
Myocardial infarction is a common cardiovascular disorder caused by prolonged ischemia,
and early diagnosis of myocardial infarction (MI) is critical for lifesaving. ECG is a simple and …
and early diagnosis of myocardial infarction (MI) is critical for lifesaving. ECG is a simple and …
An explainable recommendation framework based on an improved knowledge graph attention network with massive volumes of side information
In recent years, explainable recommendation has been a topic of active study. This is
because the branch of the machine learning field related to methodologies is enabling …
because the branch of the machine learning field related to methodologies is enabling …
[HTML][HTML] Exploring post-hoc agnostic models for explainable cooking recipe recommendations
R Yera, AA Alzahrani, L Martínez - Knowledge-Based Systems, 2022 - Elsevier
The need of increasing trustworthiness and transparency in artificial intelligence (AI)-based
systems that adhere ethical principles of respect for human autonomy, prevention of harm …
systems that adhere ethical principles of respect for human autonomy, prevention of harm …
Explainable and secure artificial intelligence: taxonomy, cases of study, learned lessons, challenges and future directions
KA Eldrandaly, M Abdel-Basset, M Ibrahim… - Enterprise Information …, 2023 - Taylor & Francis
Explainable artificial intelligence (XAI) is an evolving discipline that mainly emphasises
unboxing in these Black-Boxes. This study provides in-depth review of XAI literature together …
unboxing in these Black-Boxes. This study provides in-depth review of XAI literature together …
Protomf: Prototype-based matrix factorization for effective and explainable recommendations
Recent studies show the benefits of reformulating common machine learning models
through the concept of prototypes–representatives of the underlying data, used to calculate …
through the concept of prototypes–representatives of the underlying data, used to calculate …
Reinforced path reasoning for counterfactual explainable recommendation
Counterfactual explanations interpret the recommendation mechanism by exploring how
minimal alterations on items or users affect recommendation decisions. Existing …
minimal alterations on items or users affect recommendation decisions. Existing …
Model-agnostic counterfactual explanations of recommendations
V Kaffes, D Sacharidis, G Giannopoulos - … of the 29th ACM conference on …, 2021 - dl.acm.org
Explanations for algorithmically generated recommendations is an important requirement for
transparent and trustworthy recommender systems. When the internal recommendation …
transparent and trustworthy recommender systems. When the internal recommendation …
Shap-enhanced counterfactual explanations for recommendations
Explanations in recommender systems help users better understand why a recommendation
(or a list of recommendations) is generated. Explaining recommendations has become an …
(or a list of recommendations) is generated. Explaining recommendations has become an …
A Reusable Model-agnostic Framework for Faithfully Explainable Recommendation and System Scrutability
State-of-the-art industrial-level recommender system applications mostly adopt complicated
model structures such as deep neural networks. While this helps with the model …
model structures such as deep neural networks. While this helps with the model …
A Counterfactual Framework for Learning and Evaluating Explanations for Recommender Systems
In the field of recommender systems, explainability remains a pivotal yet challenging aspect.
To address this, we introduce the Learning to eXplain Recommendations (LXR) framework …
To address this, we introduce the Learning to eXplain Recommendations (LXR) framework …