machine learning
PulseAugur coverage of machine learning — every cluster mentioning machine learning across labs, papers, and developer communities, ranked by signal.
- instance of artificial neural network 90%
- used by graphics processing unit 90%
- instance of Gaussian Processes for Machine Learning 90%
- instance of computer science 70%
- instance of deep learning 70%
- instance of foundation model 70%
- used by artificial neural network 70%
- instance of random forest 70%
- instance of graphics processing unit 70%
- used by random forest 60%
- instance of computer vision 60%
- used by deep learning 50%
7 day(s) with sentiment data
-
New framework quantifies epistemic uncertainty in machine learning
Researchers have introduced a new framework for comparing and quantifying epistemic uncertainty in machine learning models. This framework, called the integral imprecise probability metric (IIPM), generalizes classical …
-
MetaColloc framework solves PDEs without optimization or data
Researchers have developed MetaColloc, a novel framework for solving partial differential equations (PDEs) using machine learning without requiring equation-specific optimization or data. The system meta-trains a neural…
-
New framework detects causal bias in generative AI models
Researchers have developed a new framework for detecting causal bias in generative AI systems. This methodology extends causal inference principles to address the unique complexities of generative models, which differ f…
-
New causal framework analyzes fairness in survival analysis
Researchers have developed a new causal framework to analyze fairness in time-to-event (TTE) analysis, a type of statistical modeling often used in healthcare and other high-stakes domains. This framework allows for the…
-
InferProbe offers local, private ML model testing
InferProbe is a new tool designed for local and private machine learning model testing. It allows users to apply fast perturbations to any endpoint to gain deeper insights into model behavior. The goal is to enable deve…
-
DataMaster framework automates ML data engineering for improved model performance
Researchers have developed DataMaster, a novel framework designed to automate the data engineering process for machine learning. This system aims to improve ML model performance by optimizing data selection, composition…
-
Football ML interpretations fail to transfer from elite to university leagues
A new study published on arXiv explores the transferability of machine learning interpretations in football performance analysis. Researchers found that performance determinants learned from elite European leagues did n…
-
New machine unlearning method focuses on data distributions
Researchers have introduced a novel approach to machine unlearning that focuses on the underlying data distributions rather than just model parameter updates. This method aims to infer these distributions precisely to d…
-
MEMS switches emerge as key component for quantum computing
Quantum computing, a field poised to solve complex problems, relies on qubits that maintain entangled states until measured. These systems require specialized hardware operating at near-absolute zero temperatures to min…
-
New AI model predicts wildfire ignition points at high resolution
Researchers have developed a new machine learning model called the Wildfire Ignition Set Predictor (WISP) to forecast active fires at a high resolution. Unlike previous methods that predict danger on a regional scale, W…
-
New BROS method slashes memory use in bilevel optimization
Researchers have introduced BROS, a novel method for memory-efficient single-loop bilevel optimization. This approach addresses the significant memory demands of existing methods when dealing with large neural networks …
-
Ireland university offers PhD in AI for traditional music
Maynooth University in Ireland is offering a fully funded PhD position focused on Music Information Retrieval for Irish Traditional Music. The studentship will involve research in audio signal processing, machine learni…
-
AI and ML usage in healthcare, especially clinical trials, shows rapid growth
The use of generative AI and machine learning in healthcare is rapidly expanding, particularly within clinical trials. Research in this area has seen a significant surge since 2017, with a notable increase in studies fr…
-
ML matches DL accuracy in OOD detection, offers better efficiency
A new study comparing machine learning (ML) and deep learning (DL) for out-of-distribution (OOD) detection found that both approaches achieved near-perfect accuracy on medical imaging datasets. While DL models are often…
-
New kernel regression bounds handle non-Gaussian noise
Researchers have developed new non-asymptotic probabilistic uniform error bounds for kernel regression. These bounds are designed to provide more reliable uncertainty quantification, especially for safety-critical appli…
-
MLOps: Notebook models fail in production due to conceptual, not technical, gaps
Machine learning models often perform well during development in notebooks but falter when deployed in real-world applications. This discrepancy is not primarily a technical issue but stems from a conceptual gap in unde…
-
New guideline tackles bias in health survey machine learning
A new guideline called Survey-aware Machine Learning (SaML) has been proposed to address biases in machine learning models trained on health survey data. Standard ML practices often overlook crucial survey design elemen…
-
New GPU solver cuRegOT accelerates optimal transport for machine learning
Researchers have developed cuRegOT, a new GPU-accelerated solver designed to overcome the computational challenges of optimal transport (OT) in large-scale machine learning applications. The solver addresses the limitat…
-
Quantum-inspired optimization tackles non-convex machine learning problems
Researchers have introduced a new framework called Quantum-Inspired Evolutionary Optimization (QIEO) to tackle complex non-convex optimization problems in machine learning. This approach uses a probabilistic representat…
-
New algorithm tackles utility imbalance in individualized differential privacy
Researchers have introduced INO-SGD, a novel algorithm designed to address utility imbalance in individualized differential privacy for machine learning. This imbalance occurs when data owners with stricter privacy need…