receiver operating characteristic
PulseAugur coverage of receiver operating characteristic — every cluster mentioning receiver operating characteristic across labs, papers, and developer communities, ranked by signal.
8 day(s) with sentiment data
-
New framework evaluates clustering by homogeneity-parsimony trade-off
A new paper introduces a framework for evaluating clusterings against known classes by focusing on the trade-off between homogeneity and parsimony. The proposed scores, derived from the information bottleneck principle,…
-
New AI methods tackle evolving deepfakes with geometric and memory-efficient detection
Researchers have developed new methods for detecting sophisticated face forgeries, addressing limitations in current AI models. One approach, GLID, uses geometric properties of image patches to identify forgeries, achie…
-
EEG seizure detection models made efficient with quantization and pruning
Researchers have developed methods to make deep neural networks more efficient for detecting seizures from EEG data. They explored converting a CNN into a spiking neural network, pruning EEG channels, and using INT8 qua…
-
New AquaAugmentor Algorithm Boosts Water Potability Prediction Accuracy
Researchers have introduced AquaAugmentor, a novel feature augmentation algorithm designed to improve the accuracy of machine learning models in predicting water potability. This algorithm is particularly effective for …
-
New framework probes clinical covariate dependence in prostate MRI grading models
Researchers have developed a novel causal-reasoning framework to analyze how deep learning models for prostate MRI grading incorporate clinical covariates. This adversarial approach aims to distinguish between useful di…
-
New research flags "administrative-cutoff leakage" in survival models
A new research paper identifies a potential pitfall in survival models that use time-indexed inputs, particularly in clinical prediction. The study highlights a phenomenon called "administrative-cutoff leakage," where m…
-
New nonlinear methods improve AI attribution over Shapley value
Researchers have developed new nonlinear axiomatic attribution methods to address limitations in the traditional Shapley value, particularly its linearity which can obscure important player contributions. These novel me…
-
Image encoder choice significantly impacts GCN performance in breast ultrasound classification
A new study explores the impact of image encoder choices on the performance of graph convolutional networks (GCNs) for breast ultrasound classification. Researchers found that higher-capacity image encoders, including b…
-
AI detects underground tunnels using GPR without labeled data · 2 sources tracked
Researchers have developed an unsupervised method for detecting underground tunnels using ground-penetrating radar (GPR). The system employs a denoising convolutional autoencoder to learn normal subsurface patterns and …
-
AI-evolved algorithms outperform human methods in link prediction · 1 source tracked
Researchers have utilized automated code-evolution systems, incorporating large language models and genetic algorithms, to develop novel methods for link prediction in complex networks. These machine-designed methods ha…
-
New ALDM model enhances few-shot 3D MRI synthesis for gliomas
Researchers have developed the Anatomically-conditioned Latent Diffusion Model (ALDM), a novel framework designed for efficient, few-shot 3D volumetric MRI synthesis. This model employs a two-stage process, first learni…
-
Study explores AI for filtering low-accessibility web pages
Researchers have developed a feasibility study for automatically filtering low-accessibility web pages, specifically addressing color vision deficiency. Their prediction model achieved a maximum Area Under the Curve (AU…
-
New research probes LLM inference, privacy, and code stylometry
Recent research explores the internal workings and security of large language models (LLMs). One study investigates how LLMs might form abstract representations similar to the human hippocampus to support inference, fin…
-
New Cross-AUC metric offers realistic evaluation for deepfake detectors
Researchers have introduced a new metric called Cross-AUC to better evaluate the performance of deepfake detectors. Traditional methods using Area Under the ROC Curve (AUC) can be misleading when detectors encounter dat…
-
Researchers review ROC curve and prove area beneath it interpretation
This paper provides a comprehensive review of the Receiver Operating Characteristic (ROC) curve, a common metric for evaluating binary classifiers. It formalizes the probabilistic interpretation of the area under the RO…