PROBLEMS WITH SHAP AND LIME IN INTERPRETABLE AI FOR EDUCATION: A COMPARATIVE STUDY OF POST-HOC EXPLANATIONS AND NEURAL-SYMBOLIC RULE EXTRACTION

Problems With SHAP and LIME in Interpretable AI for Education: A Comparative Study of Post-Hoc Explanations and Neural-Symbolic Rule Extraction

Given that education is classified as a ‘high-risk’ domain under regulatory frameworks like the EU AI Act, ensuring accurate and trustworthy interpretability in educational AI applications is critical due to its profound impact on student learning and development.This study compares a knowledge-based artificial neural network (KBANN)

read more

Methods to address poultry robustness and welfare issues through breeding and associated ethical considerations.

As consumers and society in general become more aware of ethical and moral dilemmas associated with confined rearing systems, pressure is put on the animal and poultry industries to adopt alternative forms of housing.This presents challenges especially regarding managing competitive social interactions between animals.However, selective breeding pr

read more


Removal of as(V), Cr(VI) and Cr(III) heavy metal ions from environmental waters using amidoxime and quaternized hydrogels

Acrylonitrile (AN) and 1-vinyl imidazole (VI) based hydrogel was prepared in bulk (macro) dimensions via redox polymerization technique.Afterward, this hydrogel was quaternized (positively charged) and exposed to the amidoximation reaction.The prepared hydrogels (quart-p(AN-co-VI), amid-p(AN-co-VI) and p(VI)) characterized using fourier transform i

read more

Interactive Trunk Extraction from Forest Point Cloud

For forest management or monitoring, it is required to constantly measure several parameters of each tree, such as height, diameter at breast height, Dip Sets and trunk volume.Terrestrial laser scanner has been used for this purpose instead of human workers to reduce time and cost for the measurement.In order to use point cloud captured by terrestr

read more