explainable AI
PulseAugur coverage of explainable AI — every cluster mentioning explainable AI across labs, papers, and developer communities, ranked by signal.
- instance of DagsHub 90%
- instance of alphaXiv 90%
- instance of SpaceXAI 90%
- instance of Gotit.pub 90%
- instance of ScienceCast 90%
- instance of artificial neural network 90%
- uses federated learning 90%
- authored by alphaXiv 70%
- instance of machine learning 70%
- authored by Gotit.pub 70%
- used by SpaceXAI 70%
- used by machine learning 70%
9 day(s) with sentiment data
-
MLLMs tested as human surrogates for Explainable AI evaluation
Researchers have explored the use of Multimodal Large Language Models (MLLMs) as a substitute for human evaluation in the field of Explainable AI (XAI). A new framework was developed to measure explanation utility for b…
-
New XposedMIA framework exploits AI explanations for membership inference attacks
Researchers have developed XposedMIA, a novel framework that exploits explainable AI (XAI) outputs to perform membership inference attacks (MIAs) on machine learning models. This method repurposes the local surrogate ge…
-
New B-XAIC dataset benchmarks explainable AI for molecular graph neural networks
Researchers have introduced B-XAIC, a new benchmark dataset designed to evaluate explainable AI (XAI) methods specifically for graph neural networks (GNNs) in the field of cheminformatics and drug discovery. This benchm…
-
New framework unifies XAI and NSAI for trustworthy IoT anomaly detection
Researchers have introduced a new analytical framework designed to enhance the trustworthiness of anomaly detection systems within the Internet of Things (IoT). This framework aims to unify approaches from Explainable A…
-
Symbolic regression shows promise for predicting pig farrowing times
Researchers have explored the use of symbolic regression, a type of explainable AI, to improve precision livestock farming, specifically for predicting farrowing time in pigs. This method generates interpretable mathema…
-
Symbolic Regression enhances AI for predicting pig farrowing times
Researchers are exploring the use of explainable artificial intelligence (XAI) for precision livestock farming, specifically to predict farrowing time in pigs. The study utilized acceleration sensor data from sows and e…
-
Board gender diversity linked to emissions performance, study finds
A research paper explored the relationship between board gender diversity (BGD) and emissions performance (EP) in European firms from 2016 to 2022. Using panel regressions, machine learning, and explainable AI, the stud…
-
XAI-Guided Framework Enhances Sim-to-Real Transfer for Autonomous Driving
Researchers have developed a novel framework called XFD, which uses explainable AI (XAI) to improve the transfer of deep reinforcement learning policies from simulation to the real world for autonomous driving. This met…
-
PostgreSQL WAL analysis, AI chatbot routing, ISO 42001, and Micro-SaaS backends
This cluster covers several distinct technical topics, including PostgreSQL's EXPLAIN command for analyzing Write-Ahead Logging (WAL) generation during database operations, the concept of routing and handoffs in AI chat…
-
New paper critiques Explainable AI metrics for failing to build trust
A new position paper published on arXiv critiques the current state of Explainable Artificial Intelligence (XAI) metrics, arguing that they often fail to increase trust in machine learning models and can instead lead to…
-
New DictXAI method enhances AI explainability with concept dictionaries
Researchers have introduced DictXAI, a novel method for Explainable AI (XAI) that aims to improve model transparency by defining concepts directly in the input domain. Unlike existing XAI techniques that rely on interpr…
-
FlowCF method offers sparse counterfactual explanations for tabular data
Researchers have introduced FlowCF, a novel model-agnostic method for generating sparse counterfactual explanations for mixed-type tabular data. This approach frames counterfactual generation as a sparse transport probl…
-
AI research proposes explainable failure prediction for maritime systems
This paper explores the application of artificial intelligence, machine learning, digital twins, and predictive maintenance to forecast and prevent equipment failures in maritime systems. It addresses the critical chall…
-
8 Advanced AI Terms Explained Beyond Basic Concepts
This article introduces eight advanced AI terms that go beyond basic concepts like tokens and prompts. It aims to equip readers with a deeper understanding of the field, covering topics such as generative artificial int…
-
New adversarial attacks target deep reinforcement learning-based intrusion detection systems
Researchers have developed new methods for generating universal adversarial perturbations (UAPs) specifically designed to degrade the performance of deep reinforcement learning (DRL)-based intrusion detection systems (I…
-
New research tackles AI explainability with novel metrics and frameworks
Two new research papers address the challenge of explaining complex AI models. The first paper introduces ExCIR (Explainability through Correlation Impact Ratio), a novel metric designed to accurately rank correlated fe…
-
CNN-Transformer Hybrid Achieves 99% Accuracy in Breast Cancer Detection
Researchers have developed a novel deep learning model that integrates Convolutional Neural Networks (CNNs) with Compact Convolutional Transformers (CCT) for improved breast cancer mammography detection and classificati…
-
New XAI method interprets hierarchical structure of speaker embeddings
Researchers have developed a new method, Hierarchical Cluster-Class Matching (HCCM), to interpret the organization of speaker embeddings within neural networks from an Explainable AI (XAI) perspective. By applying a hie…
-
New XAI method generates perceptible counterfactual examples using expert knowledge
A new research paper introduces DiCEf, an extension of the DiCE method for generating counterfactual examples (CFEs) in explainable AI (XAI). This enhanced method integrates expert knowledge through a fuzzy linguistic v…
-
AI's role in judging political debates and democracy examined
The use of AI in political debates is being examined, with a focus on whether algorithms can remain neutral when judging such discussions. This exploration delves into the concept of Algorithmic Neutrality and the impor…