Fourier Neural Operators
PulseAugur coverage of Fourier Neural Operators — every cluster mentioning Fourier Neural Operators across labs, papers, and developer communities, ranked by signal.
2 天有情绪数据
-
混合物理信息神经网络推动电力系统设计
一篇新的综述文章探讨了使用混合物理信息神经网络（PIML）来增强电力系统。这些方法将物理定律嵌入机器学习模型，提高了准确性和效率，尤其是在数据稀缺的情况下。文章详细介绍了各种PIML架构及其在故障检测和数字孪生等领域的应用，强调了它们优于纯数据驱动的方法。
-
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模型高保真度预测海上风力涡轮机尾流
研究人员开发了一种使用傅里叶神经网络算子（FNO）和物理信息神经网络（PINNs）对浮动式海上风力涡轮机动态尾流进行建模的新方法。研究发现，与PINNs相比，FNO在捕捉复杂湍流结构和预测各种频率下的尾流行为方面更有效。FNO还显示出显著更快的训练时间，收敛速度比PINNs快八倍。
-
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…