automatic differentiation
PulseAugur coverage of automatic differentiation — every cluster mentioning automatic differentiation across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New research explores physics-informed neural networks and operators · 10 sources tracked
Multiple research papers explore advancements in physics-informed neural networks (PINNs) and neural operators. One study investigates whether improved scores in machine learning models directly translate to better phys…
-
New research tackles PINN limitations for solving PDEs · 4 sources tracked
Recent research explores advancements in physics-informed neural networks (PINNs) for solving partial differential equations (PDEs). One paper introduces a physics-informed random feature method to address spectral bias…
-
New arXiv papers benchmark optimizers and debias PINNs for inverse problems
Two new arXiv papers explore solving inverse problems using differentiable physics simulators and physics-informed neural networks (PINNs). The first paper benchmarks various optimizers across 12 differentiable physics …
-
Research compares automatic differentiation and discretization for AI-powered PDE solvers
A new research paper systematically analyzes the trade-offs between automatic differentiation (AD) and discretization-based constraints for physics-informed neural networks (PINNs) used in solving partial differential e…
-
New method uses ML to find periodic orbits in dynamical systems
Researchers have developed a new Hessian-based method for numerically continuing periodic orbits in dynamical systems, utilizing Fourier series to parameterize orbits and automatic differentiation for Jacobian automatio…
-
New framework simplifies neural network mixed-effects model implementation
Researchers have developed a new framework for implementing neural network mixed-effects models (NMMs) using Template Model Builder (TMB). This approach leverages automatic differentiation and Laplace approximation, all…
-
New PINN-based framework solves complex HJI equations
Researchers have developed a new framework that combines dynamic programming with physics-informed neural networks (PINNs) to solve complex mathematical equations known as Hamilton--Jacobi--Isaacs (HJI) equations. This …
-
New research explores finite-difference methods for PINNs
A new paper explores the use of finite-difference (FD) methods for computing derivatives in Physics-Informed Neural Networks (PINNs), presenting it as an alternative to automatic differentiation (AD). The research demon…
-
Finite-difference methods offer faster, more accurate derivatives for PINNs
A new paper explores finite-difference (FD) methods as an alternative to automatic differentiation (AD) for computing derivatives in physics-informed neural networks (PINNs). The research indicates that FD can match AD …
-
New solver-level differentiation method enhances differentiable simulations
Researchers have developed a new method called solver-level differentiation for creating differentiable simulations. This approach differentiates the executed solver directly, rather than the converged equation or relyi…
-
Quantum classifiers show inherent defense against gradient attacks due to measurement costs
Researchers have analyzed the cost of adversarial attacks against quantum classifiers, finding that finite quantum measurement statistics, or shot noise, can act as a defense mechanism. The study quantifies the measurem…
-
New methods explore gradient-free optimization for neural networks
Researchers are exploring novel methods for optimizing neural networks without relying on traditional gradient-based approaches. One paper introduces a first-order layer for differentiable optimization that avoids compu…
-
New algorithms accelerate optimization for machine learning and spectrum cartography
Researchers have developed new methods for accelerating optimization algorithms, specifically focusing on randomized-subspace Nesterov accelerated gradient techniques. These methods aim to reduce computational costs by …