Neural Physics: Using AI Libraries to Develop Physics-Based Solvers for Incompressible Computational Fluid Dynamics

arXiv — cs.LG•Thursday, November 6, 2025 at 5:00:00 AM

A recent study explores the innovative use of AI libraries to create physics-based solvers for incompressible computational fluid dynamics. By treating numerical discretizations of partial differential equations as convolutional layers in neural networks, researchers aim to enhance the efficiency and accuracy of simulations. This approach not only leverages the power of AI but also offers a new perspective on solving complex fluid dynamics problems, potentially revolutionizing the field and making advanced simulations more accessible.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

LucidQuery AI

Combines diffusion reasoning with autoregressive LLM for advanced AI analysis.

AI & DataTry the app

Dyad

Build and deploy free, local AI applications with open-source tools.

AI & DataTry the app

Fluidwave

Access AI productivity tools and hire human assistants from our marketplace.

AI & DataTry the app

Continue Readings

arXiv — cs.LG2 days ago

CoGraM: Context-sensitive granular optimization method with rollback for robust model fusion

PositiveArtificial Intelligence

CoGraM (Contextual Granular Merging) is a newly introduced optimization method designed to enhance the merging of neural networks without retraining, addressing issues of accuracy and stability that are prevalent in existing methods like Fisher merging. This multi-stage, context-sensitive approach utilizes rollback mechanisms to prevent harmful updates, thereby improving the robustness of the merged network.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Why Rectified Power Unit Networks Fail and How to Improve It: An Effective Field Theory Perspective

PositiveArtificial Intelligence

The introduction of the Modified Rectified Power Unit (MRePU) activation function addresses critical issues faced by deep Rectified Power Unit (RePU) networks, such as instability during training due to vanishing or exploding values. This new function retains the advantages of differentiability and universal approximation while ensuring stable training conditions, as demonstrated through extensive theoretical analysis and experiments.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Learning to Solve Constrained Bilevel Control Co-Design Problems

NeutralArtificial Intelligence

A new framework for Learning to Optimize (L2O) has been proposed to address the challenges of solving constrained bilevel control co-design problems, which are often complex and time-sensitive. This framework utilizes modern differentiation techniques to enhance the efficiency of finding solutions to these optimization problems.

Read full article

via arXiv — cs.LG

arXiv — stat.ML2 days ago

Comparison of neural network training strategies for the simulation of dynamical systems

PositiveArtificial Intelligence

A recent study has compared two neural network training strategies—parallel and series-parallel training—specifically for simulating nonlinear dynamical systems. The empirical analysis involved five neural network architectures and practical examples, including a pneumatic valve test bench and an industrial robot benchmark. The findings indicate that while series-parallel training is prevalent, parallel training offers superior long-term prediction accuracy.

Read full article

via arXiv — stat.ML

arXiv — cs.LG3 days ago

Mixed precision accumulation for neural network inference guided by componentwise forward error analysis

PositiveArtificial Intelligence

A new study proposes a mixed precision accumulation strategy for neural network inference, utilizing a componentwise forward error analysis to optimize error propagation in linear layers. This method suggests that the precision of each output component should be inversely proportional to the condition numbers of the weights and activation functions involved, potentially enhancing computational efficiency.

Read full article

via arXiv — cs.LG

arXiv — cs.LG3 days ago

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry

NeutralArtificial Intelligence

Sparse Autoencoders (SAEs) have been analyzed to determine their effectiveness in uncovering meaningful concepts within neural network representations. A unified framework has been introduced, framing SAEs as solutions to a bilevel optimization problem, which highlights the inherent biases in concept detection based on the structural assumptions of different SAE architectures.

Read full article

via arXiv — cs.LG

arXiv — cs.LG3 days ago

Verifying Closed-Loop Contractivity of Learning-Based Controllers via Partitioning

PositiveArtificial Intelligence

A recent study has introduced a method for verifying closed-loop contractivity in nonlinear control systems using neural networks for both controllers and contraction metrics. This approach employs interval analysis and a domain partitioning strategy to ensure that the dominant eigenvalue of a symmetric Metzler matrix remains nonpositive, which is essential for confirming contractivity. The method was validated on an inverted pendulum system, showcasing its effectiveness in training neural network controllers.

Read full article

via arXiv — cs.LG

arXiv — stat.ML3 days ago

Using physics-inspired Singular Learning Theory to understand grokking & other phase transitions in modern neural networks

PositiveArtificial Intelligence

A recent study has applied Singular Learning Theory (SLT), a physics-inspired framework, to better understand the complexities of modern neural networks, particularly focusing on phenomena like grokking and phase transitions. The research empirically tests SLT in various toy models, including a grokking modulo-arithmetic model and Anthropic's Toy Models of Superposition, to explore the scaling of learning coefficients with problem difficulty.

Read full article

via arXiv — stat.ML