Sindy
PulseAugur coverage of Sindy — every cluster mentioning Sindy across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
LLM Agents Autonomously Discover Bioprocess Kinetics
Researchers have developed a novel LLM-driven agent framework for autonomously discovering the dynamics and kinetics of bioprocesses. This closed-loop architecture uses a sequential "isolation-peeling" methodology combi…
-
New WARP method enhances PDE discovery from data for fluid and plasma simulations
Researchers have developed a new method called Weak-form Anchored Rollout for PDEs (WARP) to discover governing partial differential equations (PDEs) from data. This technique addresses limitations in existing sparse re…
-
New framework PSI-SINDy enhances reliability of identifying nonlinear dynamics
Researchers have developed PSI-SINDy, a new statistical inference framework designed to quantify the reliability of dynamical terms identified by the Sparse Identification of Nonlinear Dynamics (SINDy) method. This appr…
-
New AI simulator probe tests response fidelity on chaotic systems
A new research paper introduces a "Response Theory Probe" to evaluate the accuracy of AI simulators for chaotic and stochastic systems. This method, tested on the Lorenz-63 model, assesses how well these simulators resp…
-
New SD-DPC framework learns interpretable feedback policies for nonlinear systems
Researchers have developed a new framework called Sparse Dictionary Differentiable Predictive Control (SD-DPC) for learning interpretable feedback policies for nonlinear systems. This method first identifies a predictio…
-
New Neural Symbolic Regression framework combines deep learning with sparse modeling
Researchers have developed a new Neural Symbolic Regression (NSR) framework that combines neural networks with sparse modeling techniques to discover succinct mathematical expressions from data. This approach first uses…
-
Attractor geometry limits equation discovery from data, study finds
A new research paper explores the geometric properties of attractors in dynamical systems and their impact on the ability to discover governing equations from data. The study introduces a metric, lambda_min(M), derived …
-
Tutorial introduces SINDy for engineering equation recovery
A new tutorial paper introduces the Sparse Identification of Nonlinear Dynamics (SINDy) method for engineering applications. SINDy addresses limitations of traditional surrogate modeling techniques like neural networks …
-
New SINDy Method Discovers Dynamical Systems from Noisy, Multi-Fidelity Data
Researchers have developed a new method called Multi-Fidelity SINDy to discover nonlinear dynamical systems from data with varying levels of noise and fidelity. This approach extends the existing Sparse Identification o…
-
New active learning method discovers dynamics with ultra-low data
Researchers have developed a new active learning strategy to discover the governing equations of complex dynamical systems, particularly in scenarios where data is scarce. This method, building on Sparse Identification …
-
New AI framework learns system dynamics without domain expertise
Researchers have developed LeARN, a new framework for system identification that uses machine learning to discover mathematical models of dynamical systems. Unlike previous methods like SINDy, LeARN learns the necessary…
-
New AI Method Discovers Dynamical System Equations
Researchers have developed a novel data-driven method for discovering the governing equations of dynamical systems. This approach utilizes complex-valued product-unit networks, which learn relevant complex monomials dir…