Deeponet
PulseAugur coverage of Deeponet — every cluster mentioning Deeponet across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New AI model predicts bridge structural responses with 60x speedup · 2 sources tracked
Researchers have developed an adaptive-trunk DeepONet model to improve the prediction of localized structural responses in long-span roadway bridges. This new framework uses a k-nearest neighbors (KNN) strategy to dynam…
-
New neural network architectures tackle complex scientific computing problems · 8 sources tracked
Researchers are developing novel neural network architectures to solve complex partial differential equations (PDEs) and model dynamical systems. These include structure-oriented randomized neural networks (SO-RaNN) for…
-
New theory advances Q-learning in continuous stochastic control
Researchers have published a paper on arXiv detailing a theoretical advancement in Q-learning, a fundamental algorithm in reinforcement learning. The study focuses on the mathematical underpinnings of Q-learning within …
-
New FNO Architectures Enhance High-Frequency Learning and Physical Accuracy
Researchers have developed new frameworks for Fourier Neural Operators (FNOs) to improve their ability to learn high-frequency information and physical properties. SirenFNO leverages sinusoidal representation networks t…
-
New AI model reduces need for labeled simulation data
Researchers have introduced PI-JEPA, a novel pretraining framework for neural operators designed to reduce the need for extensive labeled simulation data in multiphysics simulations. This method leverages unlabeled para…
-
AI framework enhances SMR simulations for digital twins
Researchers have developed a novel framework combining reduced-order models (ROMs) with neural operators for computational fluid dynamics (CFD) simulations. This approach aims to enable real-time thermal-hydraulic simul…
-
New Theory Explains Neural Scaling Laws in Operator Learning
This paper presents a theoretical framework for understanding neural scaling laws in deep operator networks, specifically focusing on architectures like DeepONet. The study analyzes approximation and generalization erro…
-
ML models predict reactor flow fields using CFD data
Researchers have developed a high-fidelity modeling framework combining computational fluid dynamics (CFD) with machine learning to characterize flow fields in pressurized water reactors. This approach uses physics-info…
-
New AI methods tackle complex differential equations
Researchers are exploring novel neural network architectures and training methodologies to enhance the solution of complex differential equations. Papers introduce reformulated neural operators that incorporate an auxil…
-
New operator-based frameworks advance multi-task deep learning theory
Researchers have developed new theoretical frameworks for understanding generalization in multi-task deep learning. One approach utilizes an operator-theoretic framework, combining Koopman-based methods with sketching t…
-
Sensoformer AI model improves sim-to-real inference for sensor data
Researchers have developed Sensoformer, a novel set-attention framework designed to improve inference from sparse and variable sensor data. By integrating Physics-Structured Domain Randomization (PSDR), the model learns…
-
Deep Operator Networks predict composite material deformation with uncertainty quantification
Researchers have developed a Deep Operator Network (DeepONet) to predict process-induced deformation in carbon/epoxy composites. This data-driven surrogate model combines physics-based simulations with experimental meas…
-
DeepONet learns Helmholtz equation operator for non-parametric 2D geometries
Researchers have developed a physics-informed neural operator network, DeepONet, to solve the 2D Helmholtz equation on non-parametric domains. This approach learns the relationship between a scatterer's geometry and the…
-
New method uses implicit layers to solve stiff differential-algebraic equations
Researchers have developed a novel approach for learning operator models of stiff differential-algebraic systems, which are notoriously difficult for neural networks. Their method utilizes an extended Newton implicit la…
-
Neural operators achieve real-time TBI modeling with multimodal fusion
Researchers have developed multimodal neural operator architectures capable of predicting full-field brain displacement from heterogeneous inputs, including neuroimaging, demographic data, and acquisition metadata. This…