Shap
PulseAugur coverage of Shap — every cluster mentioning Shap across labs, papers, and developer communities, ranked by signal.
- used by streamlit 90%
- instance of Local Interpretable Model-Agnostic Explanations for Classification of Lymph Node Metastases 70%
- competes with Local Interpretable Model-Agnostic Explanations for Classification of Lymph Node Metastases 70%
- used by ScienceCast 70%
- competes with Local Interpretable Model Agnostic Explanations 70%
- used by CatalyzeX 70%
- instance of alphaXiv 70%
- used by alphaXiv 70%
- instance of Local Interpretable Model Agnostic Explanations 70%
- competes with ScienceCast 70%
- used by Gotit.pub 70%
- used by logistic regression model 70%
14 day(s) with sentiment data
-
LLMs enhance frozen fraud detectors by patching blind spots
Researchers have developed a novel framework to enhance the performance of frozen fraud detection models by using Large Language Models (LLMs) to identify and address blind spots. This method proposes rules based on fea…
-
ConceptTime uses predictive surprise for interpretable time-series analysis
Researchers have developed ConceptTime, a novel self-supervised method for time-series classification that achieves high accuracy and interpretability without requiring labeled data. The approach uses "predictive surpri…
-
AI enhances MRI brain tumor detection with deep learning and SHAP analysis
Researchers have developed an enhanced method for detecting brain tumors using Magnetic Resonance Imaging (MRI) by combining deep learning techniques with explainable AI. The study explored various feature representatio…
-
New dataset AraEngage analyzes Arabic Facebook news engagement
Researchers have developed AraEngage, a dataset of 10,000 Arabic Facebook news posts, to analyze linguistic features associated with user engagement. The study found that religious expressions, message length, sentence …
-
New framework integrates volatility measurement and forecasting
Researchers have introduced Neural Realized Measures (NRM), a novel framework for volatility forecasting that integrates the measurement and prediction stages. Unlike traditional methods that first compress intraday dat…
-
Amazon Marketplace uses AI to improve A+ Content quality
Amazon Marketplace is employing Amazon SageMaker AI to enhance the quality of "A+ Content," which includes text, images, and videos on product detail pages. This initiative aims to provide selling partners with actionab…
-
Deep learning and SHAP analysis enhance MRI brain tumor detection
Researchers have developed an enhanced method for detecting brain tumors using Magnetic Resonance Imaging (MRI) combined with deep learning and explainable AI. The study explored various feature representation schemes, …
-
New framework designs spatial descriptors for materials property prediction
Researchers have developed a new framework for creating spatial descriptors to predict local spectra and hysteresis loops in materials science. This approach uses a genetic algorithm to optimize spatial partitions and p…
-
AI forensic pipeline ensures model integrity for intrusion detection
Researchers have developed MODEXRE, a forensic pipeline designed to ensure the integrity and verifiability of explainable AI models used in intrusion detection. The system extends a previously validated XGBoost classifi…
-
AI text detectors struggle with domain shifts, new xAI study finds
A new research paper explores the limitations of current AI text detection models, particularly when faced with domain shifts. The study, which analyzed models like DistilBERT and RoBERTa using LLMs such as Llama 3 and …
-
AI models evaluated for IoT DDoS detection under resource constraints
A new research paper evaluates several pre-trained convolutional neural network architectures for detecting distributed denial-of-service (DDoS) attacks in resource-constrained Internet of Things (IoT) environments. The…
-
AI framework enhances fraud detection in digital banking
This study introduces a novel framework for detecting fraud in digital banking, particularly addressing challenges like imbalanced data and operational limits. The framework incorporates chronological evaluation, featur…
-
New CBFI framework aims to reveal hidden interactions in ML models
Researchers have developed a new framework called localized case-based feature importance (CBFI) to better understand the decision-making processes of complex machine learning models. Unlike existing methods like SHAP a…
-
Hybrid SEIR-TFT framework enhances pandemic forecasting with explainable AI
Researchers have developed a hybrid forecasting framework that combines an SEIR epidemiological model with a Temporal Fusion Transformer (TFT) to predict pandemic spread. This approach integrates epidemiological data, i…
-
New CBFI framework disentangles feature interactions in ML models
Researchers have developed a new framework called localized case-based feature importance (CBFI) to better understand the internal workings of machine learning models. This method aims to disentangle individual feature …
-
New framework offers interpretable singing emotion recognition
Researchers have developed a new framework for interpretable singing emotion recognition that utilizes singing-specific acoustic and vocal technique features. This approach aims to provide deeper insights into the vocal…
-
New ACAGS framework enhances AI agent security in digital commerce
Researchers have developed a new cybersecurity framework called the Autonomous Commerce Agent Guard System (ACAGS) to secure AI agents involved in digital commerce. This system uses machine learning, behavioral analytic…
-
New metric measures AI explanation fairness across demographics
Researchers have developed a new metric, Plausibility-EFG, to measure disparities in how AI models explain their decisions across different demographic groups, specifically in hate speech detection. Using the HateXplain…
-
AI model estimates biological age using diverse clinical data and SHAP
Researchers have developed a novel machine-learning framework to estimate biological age using a CatBoost regression model and SHAP for interpretability. This model was trained on a large dataset from the US National He…
-
SHAP attribution methods show weak causal faithfulness in language models
Researchers have evaluated the effectiveness of SHAP as an attribution method for sparse autoencoder (SAE) features in language models. Their study, using sentiment classification on the SST-2 benchmark with GPT-2 Small…