Results 21 to 30 of about 1,818,152 (349)
Toward Practical Usage of the Attention Mechanism as a Tool for Interpretability
IEEE Access, 2022 Natural language processing (NLP) has been one of the subfields of artificial intelligence much affected by the recent neural revolution. Architectures such as recurrent neural networks (RNNs) and attention-based transformers helped propel the state of ...
Martin Tutek, Jan Snajder
doaj +1 more source
Explaining Explanations: An Overview of Interpretability of Machine Learning [PDF]
International Conference on Data Science and Advanced Analytics, 2018 There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought processes.
Leilani H. Gilpin +5 more
semanticscholar +1 more source
A Survey on Neural Network Interpretability [PDF]
IEEE Transactions on Emerging Topics in Computational Intelligence, 2020 Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems.
Yu Zhang +3 more
semanticscholar +1 more source
Prediction or interpretability?
Emerging Themes in Epidemiology, 2019 The journal published a review of the literature on recursive partition in epidemiological research comparing two decision tree methods: classification and regression trees (CARTs) and conditional inference trees (CITs).
Stefano Nembrini
doaj +1 more source
Re-interpreting rules interpretability
International Journal of Data Science and Analytics, 2022 Abstract Trustworthy machine learning requires a high level of interpretability of machine learning models, yet many models are inherently black-boxes. Training interpretable models instead—or using them to mimic the black-box model—seems like a viable solution. In practice, however, these interpretable models are still unintelligible
Adilova, L. +3 more
openaire +2 more sources
npj Digital Medicine, 2023 The literature on artificial intelligence (AI) or machine learning (ML) in mental health and psychiatry lacks consensus on what “explainability” means. In the more general XAI (eXplainable AI) literature, there has been some convergence on explainability
Dan W. Joyce +3 more
semanticscholar +1 more source
SleepTransformer: Automatic Sleep Staging With Interpretability and Uncertainty Quantification [PDF]
IEEE Transactions on Biomedical Engineering, 2021 Background: Black-box skepticism is one of the main hindrances impeding deep-learning-based automatic sleep scoring from being used in clinical environments. Methods: Towards interpretability, this work proposes a sequence-to-sequence sleep-staging model,
Huy P Phan +5 more
semanticscholar +1 more source
Hierarchical Architectures of Fuzzy Models: From Type-1 fuzzy sets to Information Granules of Higher Type [PDF]
International Journal of Computational Intelligence Systems, 2010 Complex phenomena are perceived from different perspectives, diversified conceptual points of view and at various levels of granularity. Symbolic and sub-symbolic processing becomes an inherently visible computing practice.
Witold Pedrycz
doaj +1 more source
Interpretability of machine learning‐based prediction models in healthcare [PDF]
WIREs Data Mining Knowl. Discov., 2020 There is a need of ensuring that learning (ML) models are interpretable. Higher interpretability of the model means easier comprehension and explanation of future predictions for end‐users.
Gregor Stiglic +5 more
semanticscholar +1 more source
Post-hoc Interpretability for Neural NLP: A Survey [PDF]
ACM Computing Surveys, 2021 Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use. Explaining models helps to address the safety and ethical concerns and is essential for accountability ...
Andreas Madsen, Siva Reddy, A. Chandar
semanticscholar +1 more source