explainable-ai

In recent years, there has been a notable increase in the deployment of machine learning (ML) models as services (MLaaS) across diverse production software applications. In parallel, explainable AI (XAI) continues to evolve, addressing the necessity for transparency in ML models. XAI techniques aim to enhance the transparency of ML models by providing insights, in terms of model's explanations, i…

Scientific Reports, Published online: 22 May 2026; doi:10.1038/s41598-026-54289-3 Explainable machine learning-based investigation for influential parameters towards interfacial capacity of spliced glass fiber reinforced polymer bars

_AI and Ethics_ 5 (5):925-4942. 2025Every explanation faces a trade-off between informativeness and compression (Kinney and Lombrozo, 2022). On the one hand, we want to aim for as much detailed and correct information as possible, informativeness, on the other hand, we want to ensure that a human can process and comprehend the explanation, compression. Current methods in eXplainable AI (XAI) try …

The world is facing ongoing efforts to rely more on Renewable energy sources (RES) to reduce carbon emissions and protect the environment. However, integrating RES can be challenging due to their variable nature. With the development of Artificial Intelligence (AI), RES management can be enhanced and improved to overcome limitations. However, AI is often viewed as a “black box” because it lacks e…

As Machine Learning Operations (MLOps) adoption accelerates, systematic integration of explainability is imperative for reliability, transparency, and continuous quality assurance. This paper presents a scoping review examining how explainability is integrated across the MLOps lifecycle, encompassing data handling, model development, and deployment. Each phase is further analyzed through its suba…

The increasing reliance on Deep Learning models, combined with their inherent lack of transparency, has spurred the development of a novel field of study known as eXplainable AI (XAI) methods. These methods aim to enhance end-users' trust in automated systems by providing insights into the rationale behind their decisions. This paper presents a novel trust measure in XAI systems, allowing their r…

IntroductionHistopathological tissue reveals natural radial and bilateral symmetry in glandular structures, which becomes progressively disrupted during malignant transformation. Leveraging this observation, this work presents a VGG16-based deep learning model enriched with symmetry-aware interpretation for early detection of Colon Adenocarcinoma. The traditional approaches are not straightforwar…

Explainable AI (XAI) is standardly defended as a tool for making intelligent systems transparent and accountable. This paper argues that the demand for explanation imposes a structural cost that standard defenses fail to acknowledge. Drawing on Pearl’s distinction between interventional and retrospective causation, we argue that XAI misappropriates the causal apparatus designed for forward-lookin…

AI is everywhere right now - but most integrations have one big problem: They give answers, but not explanations. If you’re building real applications (customer support tools, decision systems, analytics dashboards), that’s a serious limitation. So I built something to fix that. The Problem Most AI integrations in web apps look like this: $response = AI::ask("Summarize this feedback"); And you ge…

_Minds and Machines_ 32 (1):185-218. 2022Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence, a fast-growing research area that is so far lacking in firm theoretical foundations. In this article, an expanded version of a …

SHAP needs 30 ms to explain a fraud prediction. That explanation is stochastic, runs after the decision, and requires a background dataset you have to maintain at inference time. This article benchmarks a neuro-symbolic model that produces a deterministic, human-readable explanation in 0.9 ms — as a by-product of the forward pass itself — on the Kaggle Credit Card Fraud dataset. The speedup is 33…

Moving beyond the black box to turn complex model outputs into actionable organizational strategies. The post How to Leverage Explainable AI for Better Business Decisions appeared first on Towards Data Science .

What is Explainability in AI? AI explainability refers to the degree to which the internal mechanics of an artificial intelligence system, especially those driven by complex algorithms like deep learning or large language models (LLMs), can be understood and interpreted by humans. Often framed as Explainable AI (XAI), this concept enables stakeholders to grasp how ... Read more » The post AI Expl…

Explainable AI (XAI): Making Artificial Intelligence Transparent and Trustworthy Introduction Artificial Intelligence (AI) has become an essential part of our […] The post Explainable AI (XAI): Making Artificial Intelligence Transparent and Trustworthy appeared first on Bits of Scope .

Author: Milton PosnerDate: 07.02.25 The potential applications of AI in health care are numerous and undeniable. But what happens when, say, an AI assistant relays a cancer diagnosis, but its […] The post Inside the project to make AI explainable for all, and why it matters appeared first on Khoury College of Computer Sciences .

Artificial intelligence (AI) is powering more tools and services than ever — from voice assistants to fraud detection systems. Still, how and why these systems make decisions raises serious concerns. As AI models grow in complexity, many operate as “black boxes,” delivering outputs without offering insight into their reasoning. This is where explainable AI is… The post The Role of Explainable AI …