Explainable AI
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Fundamental Limitation in Explaining AI
arXiv:2605.24727v2 Announce Type: replace Abstract: While large-scale models such as LLMs and diffusion models have achieved practical success, public institutions have emphasized the importance of explainability in AI. Existing methods for explaining AI, however, are not designed to provide completely faithful explanations of the behavior of large-scale AI systems.
Walmart shareholders reject proposal to explain AI's impact on 1.6 million employees
Walmart shareholders voted against an investor proposal asking it to report on how its use of AI is affecting the well-being of its employees, according to voting results from the retailer's annual shareholders' meeting. The proposal, filed by investor United for Respect, reportedly asks Walmart to explain how it measures the effect of advanced technologies — like Artificial Intelligence (AI) and automation — on jobs, pay, training and equity. This is Walmart's first annual meeting since...
Analysis of Information Theory for Explainable AI
Announce Type: replace Abstract: With the intervention of machine vision in our crucial day to day necessities including healthcare and automated power plants, attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network provides specific inferences. This paper proposes a novel post-hoc visual explanation method called MI CAM based on activation mapping. Differing from previous class activation mapping based approaches, MI CAM produces...
Knee-xRAI: An Explainable AI Framework for Automatic Kellgren-Lawrence Grading of Knee Osteoarthritis
arXiv:2604.23435v2 Announce Type: replace Abstract: Grading knee osteoarthritis (KOA) on plain radiographs is poorly reproducible across readers. A single-grade disagreement on the Kellgren-Lawrence (KL) scale can alter surgical management or redirect a patient from conservative therapy to intra-articular injection. Meanwhile, deep learning models that outperform human readers often offer no explanation for their decisions.
From Network Experience to Subscriber Retention: An Explainable AI Framework for Mobile Operators
arXiv:2606.04838v1 Announce Type: new Abstract: This article presents a framework for the prediction of subscriber churn in mobile operators also known as telecommunication operators (or telcos). This framework covers relevant aspects of data-driven approaches using explainable artificial intelligence and machine learning. To demonstrate the robustness of the framework, we implement it on real data from one of the globally leading telcos with tens of millions of subscribers and show results...
Explainable AI Through a Democratic Lens: DhondtXAI for D'Hondt-Projected Feature Attribution
arXiv:2411.05196v3 Announce Type: replace Abstract: This study presents DhondtXAI as a SHAP-independent, D'Hondt-based attribution framework for tabular XAI. Instead of model-native feature importance or SHAP values, DhondtXAI computes background-interventional removal effects, separates positive and negative evidence, forms optional feature alliances, applies optional thresholds, allocates seats via the D'Hondt rule, and projects onto the local model-output difference. Completeness is...
XAI-on-RAN: Explainable, AI-native, and GPU-Accelerated RAN Towards 6G
Announce Type: cross Abstract: Artificial intelligence (AI)-native radio access networks (RANs) will serve vertical industries with stringent requirements: smart grids, autonomous vehicles, remote healthcare, industrial automation, etc. To achieve these requirements, modern 5G/6G design increasingly leverage AI for network optimization, but the opacity of AI decisions poses risks in mission-critical domains. These use cases are often delivered via non-public networks (NPNs) or dedicated...
Billions spent and hypothetical returns: the AI boom explained with six charts
Expenditure is growing fast and consumer take-up accelerating. But alarm bells are sounding The race is very much on. Elon Musk’s SpaceX, which makes AI models as well as space rockets, announced last week it is seeking a $1.77tn (£1.31tn) valuation on the US stock market while Anthropic, the startup behind the Claude chatbot, said it had filed for an initial public offering.
Billions spent and hypothetical returns: the AI boom explained with six charts
Expenditure is growing fast and consumer take-up accelerating. But alarm bells are sounding The race is very much on. Elon Musk’s SpaceX, which makes AI models as well as space rockets, announced last week it is seeking a $1.77tn (£1.31tn) valuation on the US stock market while Anthropic, the startup behind the Claude chatbot, said it had filed for an initial public offering.