XCrowd: Combining Explainability and Crowdsourcing to Diagnose Models in Relation Extraction
Relation extraction methods are currently dominated by deep neural models, which capture
complex statistical patterns while being brittle and vulnerable to perturbations in data and …
complex statistical patterns while being brittle and vulnerable to perturbations in data and …
Enriched nonlinear grey compositional model for analyzing multi-trend mixed data and practical applications
H Li, N Xie, K Li - Applied Mathematical Modelling, 2024 - Elsevier
The compositional data are interrelated, and analyzing the evolution of each component is
crucial for understanding population dynamics. However, the complex structure and tedious …
crucial for understanding population dynamics. However, the complex structure and tedious …
[PDF][PDF] Responsible Reasoning-a Systematic
J Pittman, L Eddy, K Wiseman - 2024 - preprints.org
The integration of responsible artificial intelligence (RAI) principles with emerging
neurosymbolic AI (NSAI) systems is crucial for the development of fair, explainable, and …
neurosymbolic AI (NSAI) systems is crucial for the development of fair, explainable, and …
Fedelr: When Federated Learning Meets Learning with Noisy Labels
Existing research on federated learning (FL) usually assumes that training labels are of high
quality for each client, which is impractical in many real-world scenarios (eg, noisy labels by …
quality for each client, which is impractical in many real-world scenarios (eg, noisy labels by …
[PDF][PDF] Neuro-Symbolic AI in 2024: A Systematic Review
BC Colelough, W Regli - 2022 - brandoncolelough.com
Abstract Background: The field of Artificial Intelligence has undergone cyclical periods of
growth and decline, known as AI summers and winters. Currently, we are in the third AI …
growth and decline, known as AI summers and winters. Currently, we are in the third AI …