explainable ai

Explainable Artificial Intelligence through Causal Modeling

This paper proposes a novel approach to explainable artificial intelligence (XAI) that leverages causal modeling to enhance the transparency and trustworthiness of AI systems. Current XAI techniques often prioritize interpretability without considering the underlying causal relationships governing the data. We introduc...

Artificial Ignorance: An Agnotological Framework for AI Bias, Opacity, Explainability, and Governance

Artificial intelligence is generally analyzed in terms of its expanding capacity to generate, process, and organize knowledge. This paper proposes reversing that perspective by examining what AI systems do not know, cannot know, are prevented from knowing, or make increasingly difficult for human beings to know. Drawin...

Beyond Explainability: Normative Disclosure and the Declared Operating Position

Explainable AI is the dominant response to automated decision-making, on the assumption that a system able to show how it produced an output has met the conditions for accountability. That assumption fails in a specific way. Selbst and Barocas established in 2018 that explaining a model does not show its decisions to b...

Robust electricity demand forecasting approach for residential buildings using explainable AI

XAI Hybrid Local-Global Model for Brain Tumor Classification

This repository contains the research code for an XAI Hybrid Local-Global Model for Brain Tumor Classification. The proposed approach combines Local Binary Patterns (LBP) as a local texture feature descriptor with EfficientNetB0 as a deep feature extractor to perform brain tumor classification. The repository also incl...

Seminar in Algebraic Geometry (SGA) — Cumulative English Edition

Read or download the cumulative English edition (4,211 pages). This collection brings together English translations of the Seminar in Algebraic Geometry (SGA): foundational works on algebraic fundamental groups, local and étale cohomology, group schemes, intersection theory, and monodromy. The cumulative reader provide...

EMSEIF Provides an Explainable AI Framework for Multi Stakeholder Curriculum Feedback and Quality Assurance in Higher Education

GlaucoFusionNet: A Causal Inference Aware Multimodal Explainable AI Framework with Counterfactual Reasoning for Glaucoma Risk Prediction

Explainable AI for Federated Learning – Attribution of Contributions

Federated Learning (FL) offers a promising approach to training machine learning models on decentralized data sources without direct data sharing. However, the inherent lack of transparency in FL raises concerns about trust, fairness, and model reliability. This paper explores the critical need for explainable AI (XAI)...

Graph-Based Explainable AI for Complex Decision-Making

The increasing prevalence of complex AI models, particularly deep neural networks, in critical decision-making domains has raised significant concerns regarding transparency and trust. These "black-box" models often operate as opaque systems, making it challenging to understand *why* a particular decision was made. Thi...

Explainable AI for Graph Structure Discovery

Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains, including social network analysis, drug discovery, and recommendation systems, by effectively learning patterns from graph-structured data. However, a significant limitation of GNNs is their inherent opaqueness—the "black box" nature...

PROMPT AS TEXT: TOWARDS A RHETORIC AND POETICS OF HUMAN–AI CO-COMPOSITION

Abstract This article argues that the prompt—the linguistic utterance through which a human initiates and directs a generative AI system—should be understood not merely as a technical input to be optimised, but as an emerging literary-rhetorical text in its own right, and therefore a legitimate and pressing object of h...