Advances in Explainable Artificial Intelligence

Machine Learning (ML)-based Artificial Intelligence (AI) algorithms have the capability to learn from known examples, creating various abstract representations and models. When applied to unfamiliar examples, these algorithms can perform a range of tasks, including classification, regression, and fo...

Szczegółowa specyfikacja

Zapisane w:
Opis bibliograficzny
Format: Online
Język:angielski
Wydane: MDPI - Multidisciplinary Digital Publishing Institute 2024
Hasła przedmiotowe:
Dostęp online:ONIX_20240514_9783725802838_215
Etykiety: Dodaj etykietę
Nie ma etykietki, Dołącz pierwszą etykiete!
_version_ 1869518884961255424
collection Directory of Open Access Books
description Machine Learning (ML)-based Artificial Intelligence (AI) algorithms have the capability to learn from known examples, creating various abstract representations and models. When applied to unfamiliar examples, these algorithms can perform a range of tasks, including classification, regression, and forecasting, to name a few. Frequently, these highly effective ML representations are challenging to comprehend, especially in the case of Deep Learning models, which may involve millions of parameters. However, in many applications, it is crucial for stakeholders to grasp the reasoning behind the system's decisions to utilize them more effectively. This necessity has prompted extensive research efforts aimed at enhancing the transparency and interpretability of ML algorithms, forming the field of explainable Artificial Intelligence (XAI). The objectives of XAI encompass: introducing transparency to ML models by offering comprehensive insights into the rationale behind specific decisions; designing ML models that are both more interpretable and transparent, while maintaining high levels of performance;, and establishing methods for assessing the overall interpretability and transparency of models, quantifying their effectiveness for various stakeholders. This Special Issue gathers contributions on recent advancements and techniques within the domain of XAI.
format Online
id doab-20.500.12854ir-137616
institution Directory of Open Access Books
language eng
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher MDPI - Multidisciplinary Digital Publishing Institute
publisherStr MDPI - Multidisciplinary Digital Publishing Institute
record_format ojs
spelling doab-20.500.12854ir-1376162024-05-14T13:46:06Z Advances in Explainable Artificial Intelligence Gianini, Gabriele Portier, Pierre-Edouard activation function ReLU family activation function test psychological profiling predictive modeling behavioral data explainable artificial intelligence rule extraction counterfactual explanations fairness bias artificial intelligence machine learning psychiatry health mental health federated learning 6G vehicle-to-everything (V2X) quality of service quality of experience interactive machine learning decision tree classifiers transparent-by-design parallel coordinates natural language generation fact-checking explainable AI deep learning LSTM Arabic sentiment analysis Explainable AI text mining random forest multi-layer perceptron protein data bank neural network artificial neural networks knowledge representation source code analysis text classification uncertainty quantification efficiency electroencephalography convolutional variational autoencoder latent space interpretation spectral topographic maps thema EDItEUR::U Computing and Information Technology::UY Computer science Machine Learning (ML)-based Artificial Intelligence (AI) algorithms have the capability to learn from known examples, creating various abstract representations and models. When applied to unfamiliar examples, these algorithms can perform a range of tasks, including classification, regression, and forecasting, to name a few. Frequently, these highly effective ML representations are challenging to comprehend, especially in the case of Deep Learning models, which may involve millions of parameters. However, in many applications, it is crucial for stakeholders to grasp the reasoning behind the system's decisions to utilize them more effectively. This necessity has prompted extensive research efforts aimed at enhancing the transparency and interpretability of ML algorithms, forming the field of explainable Artificial Intelligence (XAI). The objectives of XAI encompass: introducing transparency to ML models by offering comprehensive insights into the rationale behind specific decisions; designing ML models that are both more interpretable and transparent, while maintaining high levels of performance;, and establishing methods for assessing the overall interpretability and transparency of models, quantifying their effectiveness for various stakeholders. This Special Issue gathers contributions on recent advancements and techniques within the domain of XAI. 2024-05-14T13:45:55Z 2024-05-14T13:45:55Z 2024 book ONIX_20240514_9783725802838_215 9783725802838 9783725802845 https://directory.doabooks.org/handle/20.500.12854/137616 eng application/octet-stream Attribution-NonCommercial-NoDerivatives 4.0 International https://mdpi.com/books/pdfview/book/8803 https://mdpi.com/books/pdfview/book/8803 MDPI - Multidisciplinary Digital Publishing Institute 10.3390/books978-3-7258-0284-5 10.3390/books978-3-7258-0284-5 46cabcaa-dd94-4bfe-87b4-55023c1b36d0 9783725802838 9783725802845 208 open access
spellingShingle activation function
ReLU family
activation function test
psychological profiling
predictive modeling
behavioral data
explainable artificial intelligence
rule extraction
counterfactual explanations
fairness
bias
artificial intelligence
machine learning
psychiatry
health
mental health
federated learning
6G
vehicle-to-everything (V2X)
quality of service
quality of experience
interactive machine learning
decision tree classifiers
transparent-by-design
parallel coordinates
natural language generation
fact-checking
explainable AI
deep learning
LSTM
Arabic sentiment analysis
Explainable AI
text mining
random forest
multi-layer perceptron
protein data bank
neural network
artificial neural networks
knowledge representation
source code analysis
text classification
uncertainty quantification
efficiency
electroencephalography
convolutional variational autoencoder
latent space interpretation
spectral topographic maps
thema EDItEUR::U Computing and Information Technology::UY Computer science
Advances in Explainable Artificial Intelligence
title Advances in Explainable Artificial Intelligence
title_full Advances in Explainable Artificial Intelligence
title_fullStr Advances in Explainable Artificial Intelligence
title_full_unstemmed Advances in Explainable Artificial Intelligence
title_short Advances in Explainable Artificial Intelligence
title_sort advances in explainable artificial intelligence
topic activation function
ReLU family
activation function test
psychological profiling
predictive modeling
behavioral data
explainable artificial intelligence
rule extraction
counterfactual explanations
fairness
bias
artificial intelligence
machine learning
psychiatry
health
mental health
federated learning
6G
vehicle-to-everything (V2X)
quality of service
quality of experience
interactive machine learning
decision tree classifiers
transparent-by-design
parallel coordinates
natural language generation
fact-checking
explainable AI
deep learning
LSTM
Arabic sentiment analysis
Explainable AI
text mining
random forest
multi-layer perceptron
protein data bank
neural network
artificial neural networks
knowledge representation
source code analysis
text classification
uncertainty quantification
efficiency
electroencephalography
convolutional variational autoencoder
latent space interpretation
spectral topographic maps
thema EDItEUR::U Computing and Information Technology::UY Computer science
topic_facet activation function
ReLU family
activation function test
psychological profiling
predictive modeling
behavioral data
explainable artificial intelligence
rule extraction
counterfactual explanations
fairness
bias
artificial intelligence
machine learning
psychiatry
health
mental health
federated learning
6G
vehicle-to-everything (V2X)
quality of service
quality of experience
interactive machine learning
decision tree classifiers
transparent-by-design
parallel coordinates
natural language generation
fact-checking
explainable AI
deep learning
LSTM
Arabic sentiment analysis
Explainable AI
text mining
random forest
multi-layer perceptron
protein data bank
neural network
artificial neural networks
knowledge representation
source code analysis
text classification
uncertainty quantification
efficiency
electroencephalography
convolutional variational autoencoder
latent space interpretation
spectral topographic maps
thema EDItEUR::U Computing and Information Technology::UY Computer science
url ONIX_20240514_9783725802838_215