Tag: Artificial neural network
Hybrid quantum GANs outperformed fully classical baselines
—
What the study found The study found that fully hybrid generative adversarial networks, meaning GANs with variational quantum circuits in both the generator and the discriminator, produced higher-quality images and better quantitative metrics than a fully classical baseline. The strongest overall performance came from using quantum blocks in both networks. Why the authors say this…
VaR-constrained S-shaped utility problem has a critical wealth threshold
What the study found The study finds a critical wealth level that determines whether the constrained optimization problem is feasible. Above that level, the problem admits a unique optimal solution and Lagrange multiplier; below it, the problem is infeasible. Why the authors say this matters The authors suggest this matters because it clarifies when an…
Framework generalizes equivariant neural layers to nonlinear homogeneous spaces
—
What the study found The paper presents a framework for nonlinear equivariant neural network layers on homogeneous spaces. The authors derive generalized steerability constraints for these layers and prove the universality of their construction. Why the authors say this matters The study suggests that its analysis of symmetry-constrained dependence on feature maps and group elements…
Joint pricing and matching lowered crowd-shipping delivery costs
What the study found The study found that a joint policy for matching orders to shoppers and setting delivery compensation can reduce delivery costs in a crowd-shipping system that uses in-store customers as couriers. The authors report that allowing multi-drop routing and flexible delivery delays also lowers operational costs. Why the authors say this matters…
EAC-Net predicts charge density with high accuracy
What the study found EAC-Net is a model for predicting real-space charge density that combines accuracy with a physically grounded atomic decomposition. The authors report that it can achieve errors typically below 1% across the periodic table and generalize well to diverse chemical environments. Why the authors say this matters The study suggests that EAC-Net…
Label noise changes information in neural representations
—
What the study found Hidden representations in neural networks change with label noise in ways that depend on how many parameters the network has. The study found a double descent pattern in the information content of these representations, and it found that overparameterized networks are robust to label noise. Why the authors say this matters…
Salivary fingerprinting and neural network identified high-risk periodontitis in diabetes
—
in MedicineLightweight neural networks analyze salivary metabolics via mass spectrometry to screen for periodontitis and diabetes, achieving 91.9% accuracy with minimal computational resources for clinical.
Fused AI framework classified enamel caries with high accuracy
Deep learning framework with quantum-inspired feature fusion achieves 99.33% accuracy for automated enamel caries classification in intraoral photographs with visual explainability.
Neural network predicts shifts in extreme weather frequency
—
in MeteorologyNeural networks leverage climate model data to predict how extreme rainfall, hail, and winds will shift geographically as climate changes, accounting for terrain effects.
Deep-learning fluorescence array quantified multiple PFAS in water
A fluorescence sensor array combined with deep learning quantifies multiple PFAS contaminants in water samples simultaneously, providing rapid screening for environmental monitoring.
