XAI-Explainable artificial intelligence [PDF]
Science Robotics, 2019 Explainability is essential for users to effectively understand, trust, and manage powerful artificial intelligence ...
Choi, J. +5 more
core +5 more sources
Structure of associative heterarchical memory
Российский технологический журнал, 2022 Objectives. Since the 20th century, artificial intelligence methods can be divided into two paradigms: top-down and bottom-up. While the methods of the ascending paradigm are difficult to interpret as natural language outputs, those applied according to ...
R. V. Dushkin +3 more
doaj +1 more source
Risk stratification and pathway analysis based on graph neural network and interpretable algorithm
BMC Bioinformatics, 2022 Background Pathway-based analysis of transcriptomic data has shown greater stability and better performance than traditional gene-based analysis. Until now, some pathway-based deep learning models have been developed for bioinformatic analysis, but these
Bilin Liang, Haifan Gong, Lu Lu, Jie Xu
doaj +1 more source
Artificial Intelligence Empowering Healthcare Services: Expert Consensus from the Mangrove Health Conference in 2025 [PDF]
Zhongguo quanke yixueArtificial intelligence (AI) demonstrates significant advantages in accelerating improvements in efficiency, accessibility, and precision of health services, thereby providing critical support for the implementation of a health-prioritized development ...
Expert Panel of the Consensus on Artificial Intelligence Empowering Healthcare Services
doaj +1 more source
Precision medicine and artificial intelligence : a pilot study on deep learning for hypoglycemic events detection based on ECG [PDF]
, 2020 Tracking the fluctuations in blood glucose levels is important for healthy subjects and crucial diabetic patients. Tight glucose monitoring reduces the risk of hypoglycemia, which can result in a series of complications, especially in diabetic patients ...
Pecchia, Leandro +3 more
core +2 more sources
Many heads but one brain: FusionBrain – a single multimodal multitask architecture and a competition
Компьютерная оптика, 2023 Supporting the current trend in the AI community, we present the AI Journey 2021 Challenge called FusionBrain, the first competition which is targeted to make a universal architecture which could process different modalities (in this case, images, texts,
D.D. Bakshandaeva +10 more
doaj +1 more source
Trustworthy artificial intelligence
Asian Journal of Philosophy, 2023 AbstractThis paper develops an account of trustworthy AI. Its central idea is that whether AIs are trustworthy is a matter of whether they live up to their function-based obligations. We argue that this account serves to advance the literature in a couple of important ways.
Mona Simion, Christoph Kelp
openaire +1 more source
Feedback Control for Passivity of Memristor-Based Multiple Weighted Coupled Neural Networks
Discrete Dynamics in Nature and Society, 2022 This paper investigates the passivity of multiple weighted coupled memristive neural networks (MWCMNNs) based on the feedback control. Firstly, a kind of memristor-based coupled neural network model with multiple weights is presented for the first time ...
Xiang-Bo Wang +4 more
doaj +1 more source
Artificial intelligence hallucinations
Critical Care, 2023 SCOPUS: le.j ; info:eu-repo/semantics ...
Salvagno, Michele +2 more
openaire +3 more sources
Capital as Artificial Intelligence [PDF]
, 2015 This article examines science-fictional allegorizations of Soviet-style planned economies, financial markets, autonomous trading algorithms, and global capitalism writ large as nonhuman artificial intelligences, focussing primarily on American science ...
Canavan, Gerry
core +2 more sources