Results 41 to 50 of about 27,667 (170)

An Interpretable Machine Learning Model to Predict Cortical Atrophy in Multiple Sclerosis

Brain Sciences, 2023
To date, the relationship between central hallmarks of multiple sclerosis (MS), such as white matter (WM)/cortical demyelinated lesions and cortical gray matter atrophy, remains unclear.
Allegra Conti, Constantina Andrada Treaba, Ambica Mehndiratta, Valeria Teresa Barletta, Caterina Mainero, Nicola Toschi   +5 more
doaj   +1 more source

Toward Building Trust in Machine Learning Models: Quantifying the Explainability by SHAP and References to Human Strategy

IEEE Access
Local model-agnostic Explainable Artificial Intelligence (XAI), such as LIME or SHAP, has recently gained popularity among researchers and data scientists for explaining black box Machine Learning (ML) models.
Zhaopeng Li, Mondher Bouazizi, Tomoaki Ohtsuki, Masakuni Ishii, Eri Nakahara   +4 more
doaj   +1 more source

A Review of Partial Information Decomposition in Algorithmic Fairness and Explainability

Entropy, 2023
Partial Information Decomposition (PID) is a body of work within information theory that allows one to quantify the information that several random variables provide about another random variable, either individually (unique information), redundantly ...
Sanghamitra Dutta, Faisal Hamman
doaj   +1 more source

Explainable analysis of infrared and visible light image fusion based on deep learning

Scientific Reports
Explainability is a very active area of research in machine learning and image processing. This paper aims to investigate the explainability of visible light and infrared image fusion technology in order to enhance the credibility of model understanding ...
Bo Yuan, Hongyu Sun, YinJing Guo, Qiang Liu, Xinghao Zhan   +4 more
doaj   +1 more source

Yet Another Discriminant Analysis (YADA): A Probabilistic Model for Machine Learning Applications

Mathematics
This paper presents a probabilistic model for various machine learning (ML) applications. While deep learning (DL) has produced state-of-the-art results in many domains, DL models are complex and over-parameterized, which leads to high uncertainty about ...
Richard V. Field, Michael R. Smith, Ellery J. Wuest, Joe B. Ingram   +3 more
doaj   +1 more source

Interpretable Optimization: Why and How We Should Explain Optimization Models

Applied Sciences
Interpretability is widely recognized as essential in machine learning, yet optimization models remain largely opaque, limiting their adoption in high-stakes decision-making.
Sara Lumbreras, Pedro Ciller
doaj   +1 more source

Explainability-driven adversarial robustness assessment for generalized deepfake detectors

EURASIP Journal on Information Security
The capabilities of generative models to produce high-quality fake images require deepfake detectors to be accurate and have strong generalization performance.
Lorenzo Cirillo, Andrea Gervasio, Irene Amerini   +2 more
doaj   +1 more source

Diagnosis of Schizophrenia Using Feature Extraction from EEG Signals Based on Markov Transition Fields and Deep Learning

Biomimetics
Diagnosing schizophrenia using Electroencephalograph (EEG) signals is a challenging task due to the subtle and overlapping differences between patients and healthy individuals.
Alka Jalan, Deepti Mishra, Marisha, Manjari Gupta   +3 more
doaj   +1 more source

Multi-branch GAT-GRU-transformer for explainable EEG-based finger motor imagery classification

Frontiers in Human Neuroscience
Electroencephalography (EEG) provides a non-invasive and real-time approach to decoding motor imagery (MI) tasks, such as finger movements, offering significant potential for brain-computer interface (BCI) applications. However, due to the complex, noisy,
Zhuozheng Wang, Yunlong Wang
doaj   +1 more source

To Explain or To Predict?

SSRN Electronic Journal, 2010
Statistical modeling is a powerful tool for developing and testing theories by way of causal explanation, prediction, and description. In many disciplines there is near-exclusive use of statistical modeling for causal explanation and the assumption that models with high explanatory power are inherently of high predictive power.
openaire   +4 more sources