explainable AI
PulseAugur coverage of explainable AI — every cluster mentioning explainable AI across labs, papers, and developer communities, ranked by signal.
- instance of ScienceCast 90%
- instance of DagsHub 90%
- uses federated learning 90%
- instance of Gotit.pub 70%
- instance of alphaXiv 70%
- used by machine learning 70%
- used by SpaceXAI 70%
- instance of machine learning 70%
- instance of Local Interpretable Model Agnostic Explanations 70%
- authored by alphaXiv 60%
- affiliated with alphaXiv 50%
- affiliated with federated learning 50%
10 day(s) with sentiment data
-
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…
-
XAI framework enhances DER cybersecurity with self-verifying anomaly detection
Researchers have developed a new explainable AI (XAI) framework called ExCYDER to enhance the cybersecurity of Distributed Energy Resources (DERs) in power grids. This framework uses a self-verifying mechanism that comb…
-
New XAI Framework Enhances LSTM Efficiency for Channel Estimation
Researchers have developed a new framework called X-RACE to improve the explainability and efficiency of deep learning models, specifically Long Short-Term Memory (LSTM) networks, used for channel estimation in high-mob…
-
New AI method discovers 'second-order patterns' in speech recognition
Researchers have introduced a novel approach to understanding how neural networks recognize speech by identifying "second-order patterns." These patterns are latent structures within the network's learned representation…
-
Explainable AI creates new attack surfaces for machine learning models
A new paper published on arXiv explores how explainable AI (XAI) techniques can inadvertently create vulnerabilities for machine learning models. The research systematizes 25 studies that leverage explanations for attac…
-
New framework detects AI model drift missed by local XAI methods
Researchers have developed a new Framework for Model Monitoring and Observability (FMMO) to address the critical risk of post-deployment drift in AI models. Traditional Explainable AI (XAI) methods, such as TreeSHAP, ca…
-
AI model detects welding defects using multi-modal data
Researchers have developed a novel deep learning model that uses multi-modal temporal attention to detect internal defects in real-time during gas metal arc welding. This model, trained on welding images and sound data …
-
New CAH method offers economic perspective on Transformer interpretability
Researchers have introduced a new method called Cumulative Asset Holdings (CAH) to interpret Transformer models, addressing perceived flaws in existing explainable AI (XAI) techniques like Generic Attention-model Explai…
-
AI researchers call for shift from XAI methods to interpretable models
A new paper published on arXiv proposes a shift in the field of explainable AI (XAI) for computer vision. The authors argue that the focus should move from developing new interpretability methods to evaluating the inter…
-
New dual-rail encoding method simplifies complex AI explanations
Researchers have developed a new method for computing explanations for complex AI decisions, addressing concerns about AI trustworthiness in critical applications. The study proves that certain types of abductive explan…
-
XAI explanations for heart rate estimation models lack direct performance correlation
Researchers have investigated the reliability and cross-dataset transferability of explainable AI (XAI) methods when applied to RhythmFormer, a model used for remote photoplethysmography (rPPG) which estimates cardiovas…
-
New TRACE framework enhances robot decision auditability
A new decision framework called TRACE has been proposed to enhance the auditability of autonomous robots powered by deep learning. This framework ensures that every decision made by a robot can be traced back to the sen…
-
Paper questions counterfactual explanations in AI for justification and recourse
A new paper explores the limitations of counterfactual explanations (CEs) in explainable AI, particularly when used for justification and recourse. The research highlights that CEs can obscure crucial design and governa…
-
Explainable AI in Computational Pathology: A New Framework Proposed
A new review paper published on arXiv addresses the fragmentation in explainable AI (XAI) research within computational pathology. The paper proposes a standardized vocabulary, a taxonomy of XAI methods, and a framework…
-
AI research paper links consistency-based diagnosis with causality explanations
A new research paper explores the connections between Consistency-Based Diagnosis (CBD) and Actual Causality/Causal Responsibility within the field of Explainable AI (XAI). The authors aim to bridge these two areas, sug…
-
New research highlights the "selection problem" in Explainable AI
Researchers have identified a significant challenge in Explainable AI (XAI) where users struggle to select the most appropriate explanation technique due to the siloed nature of current XAI interfaces. This "selection p…
-
Systematic review highlights fragmentation in time series XAI frameworks
A new systematic review published on arXiv analyzes software frameworks designed for explainable AI (XAI) in time series classification. The review identifies six frameworks that specifically support time series data, b…