Neural ODEs
PulseAugur coverage of Neural ODEs — every cluster mentioning Neural ODEs across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New theory enables zero-shot size transfer for graph neural networks
Researchers have developed a theoretical framework for zero-shot size transfer in Graph Neural Differential Equations (GNDEs) on sparse random graphs. This principle allows GNDEs trained on smaller graphs to be deployed…
-
Neural ODEs with planted attractors enhance classification tasks
Researchers have developed a novel method for classification tasks using Neural Ordinary Differential Equations (Neural ODEs) with strategically placed attractors. These attractors act as indicators for specific classes…
-
New arXiv papers explore Neural ODEs, adaptive INRs, and parameterized PDE solvers
Three new research papers have been published on arXiv, each exploring novel approaches in neural network architectures and their applications. The first paper introduces Neural ODEs with planted attractors for classifi…
-
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 Hybrid Model Learns Neuron Dynamics Using Neural ODEs
Researchers have developed a novel hybrid modeling framework that integrates neural ordinary differential equations (Neural ODEs) into biophysical neuron models. This approach allows for the flexible discovery of unknow…
-
New theory models neural ODE training dynamics
Researchers have introduced a new theoretical framework for studying neural ordinary differential equations (neural ODEs), which are used to model dynamical systems and deep learning. This framework, grounded in dynamic…
-
Neural-ODEs gain fixed-point control with provable universality
Researchers have developed a new technique for Neural Ordinary Differential Equations (Neural-ODEs) that allows them to precisely control fixed points within the system. This method ensures that the velocity field is ex…
-
PINNs with Differentiable Chemistry Solve Stiff Reaction Systems
Researchers have developed a novel framework integrating a differentiable chemistry solver with physics-informed neural networks (PINNs) to tackle stiff and parameterized reaction systems. This approach addresses limita…
-
New LTE-ODE model enhances traffic forecasting by handling continuous and discrete dynamics
Researchers have developed Local Truncation Error-Guided Neural ODEs (LTE-ODE) to improve spatiotemporal forecasting in large-scale traffic networks. Traditional Neural ODEs struggle with abrupt anomalies due to Lipschi…
-
Neural ODEs advance with mixed precision training and causal forecasting methods
Researchers have developed a new mixed-precision training framework for Neural Ordinary Differential Equations (Neural ODEs) to reduce computational costs. This framework uses low-precision computations for evaluating n…