Fourier Neural Operators
PulseAugur coverage of Fourier Neural Operators — every cluster mentioning Fourier Neural Operators across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
Hartley Neural Operator offers real-valued alternative to Fourier Neural Operators
Researchers have introduced the Hartley Neural Operator (HNO), a new model designed to mirror the capabilities of Fourier Neural Operators (FNO) but with a focus on real-valued partial differential equation (PDE) soluti…
-
New Hartley Neural Operator offers real-valued alternative to FNO for PDEs
Researchers have introduced the Hartley Neural Operator (HNO) as a real-valued alternative to Fourier Neural Operators (FNO) for solving partial differential equations. HNO utilizes the Discrete Hartley Transform, learn…
-
New testing method validates scientific ML surrogates
Researchers have developed a new method for testing scientific machine-learning (SciML) surrogates, which approximate complex simulations. The proposed approach, called Domain-Validity-Gated Metamorphic Testing, address…
-
Operator Boosting framework creates efficient neural PDE surrogates
Researchers have developed a new framework called Operator Boosting to create more efficient neural network surrogates for solving partial differential equations (PDEs). This method trains smaller neural operators on re…
-
Machine learning enhances plasma simulations via improved closure relations
A new review paper published on arXiv details the application of machine learning techniques to improve plasma simulations. The paper focuses on developing closure relations for plasma moments, which are essential for f…
-
New LFNO framework unifies Laplace and Fourier operators for dynamical systems
Researchers have developed the Laplace-Fourier Neural Operator (LFNO), a novel framework designed to model dynamical systems. LFNO uniquely combines the strengths of Laplace and Fourier Neural Operators by decomposing s…
-
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…
-
Fourier Neural Operators struggle with resolution generalization
A new research paper explores the limitations of Fourier Neural Operators (FNOs) in generalizing across different spatial resolutions. The study found that directly inferring on a finer grid does not always improve perf…
-
New diagnostic tool assesses learned physics simulators
Researchers have introduced a new diagnostic tool called normalized semigroup error to evaluate learned physics simulators. This method assesses the temporal composition and long-horizon rollout capabilities of these si…
-
Hybrid physics-informed neural networks advance electricity system design
A new review paper explores the use of hybrid physics-informed neural networks (PIML) for enhancing electricity systems. These methods embed physical laws into machine learning models, improving accuracy and efficiency,…
-
AI interpretability advances with Sparse Autoencoders for ASR and functional operators
Researchers are exploring advanced techniques for interpreting the internal workings of complex AI models. One paper details the application of Sparse Autoencoders (SAEs) to Automatic Speech Recognition (ASR) systems li…
-
Quantum models learn high-frequency functions with multi-stage residual learning
Researchers have developed a new technique to address frequency learning biases in quantum machine learning models. This method, inspired by classical Fourier Neural Operators, uses multi-stage residual learning to iter…
-
SPAMoE framework enhances full-waveform inversion with spectrum-aware neural operators
Researchers have developed SPAMoE, a novel framework designed to improve the efficiency and accuracy of full-waveform inversion (FWI) for subsurface velocity model reconstruction. This approach addresses the challenge o…
-
Isotropic Fourier Neural Operators
Researchers have introduced Isotropic Fourier Neural Operators, a modification to existing Fourier Neural Operators designed to better respect the symmetries inherent in many physical systems. This new approach improves…
-
AI models predict offshore wind turbine wakes with high fidelity
Researchers have developed a new method for modeling the dynamic wakes of floating offshore wind turbines using Fourier Neural Operators (FNOs) and Physics-Informed Neural Networks (PINNs). The study found that FNOs wer…
-
New neural operators enhance PDE solving with Shearlet and LNF-NO architectures
Two new research papers introduce novel neural operator architectures designed to improve the efficiency and accuracy of solving partial differential equations (PDEs). The first, Linear-Nonlinear Fusion Neural Operator …
-
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…