We introduce AutomataGPT, a generative pretrained transformer (GPT) trained on synthetic spatiotemporal data from 2D cellular automata to learn symbolic rules. Demonstrating strong performance on both forward and inverse tasks, AutomataGPT establishes a scalable, domain‐agnostic framework for interpretable modeling, paving the way for future ...
Jaime A. Berkovich +2 more
wiley +1 more source
Improved predictive formulae for wave overtopping at sloped breakwaters using interpretable machine learning models. [PDF]
Habib MA +3 more
europepmc +1 more source
Consensus Formation and Change are Enhanced by Neutrality
Neutral agents are shown to enhance both the formation and overturning of consensus in collective decision‐making. A general mathematical model and experiments with locusts and humans reveal that neutrality enables robust consensus via simple interactions and accelerates consensus change by reducing effective population size.
Andrei Sontag +3 more
wiley +1 more source
Sensitivity Analysis: A Practical Guide to Teaching. [PDF]
Tarantola S +6 more
europepmc +1 more source
Evaluating the Utilities of Foundation Models in Single‐Cell Data Analysis
This study delivers the first systematic, task‐level evaluation of single‐cell foundation models across eight core analytical tasks. By benchmarking 10 leading models with the scEval framework, it reveals where foundation models truly add value, where task‐specific methods still dominate, and provides concrete, reproducible guidelines to steer the next
Tianyu Liu +4 more
wiley +1 more source
Numerical robustness of COVID-19 model with Lyapunov stability analysis. [PDF]
Pandey A, Ghosh S.
europepmc +1 more source
Neuid: A Novel Neuron‐Enriched LncRNA that Connects Epigenetic Gene Silencing to Alzheimer's Disease
ABSTRACT The increasing evidence that non‐coding RNAs can become deregulated during pathogenesis is dramatically expanding the space for drug discovery beyond the protein‐coding genome. Long noncoding RNAs (lncRNAs) are emerging as key regulators of cellular function, yet most remain uncharacterized.
Ranjit Pradhan +17 more
wiley +1 more source
A Monte Carlo-Based Framework for Two-Stage Stochastic Programming: Application to Bond Portfolio Optimization. [PDF]
Albaqami H, Mrad M, Gharbi A, Subasi MM.
europepmc +1 more source
Spatial‐Wavelength Multiplexing Error‐Controlled Photonic Analog Computing System
A novel photonic integrated circuit prototype implementing the concept of general‐purpose analog computing and demonstrate its capability in radio frequency applications. The chip features a multichannel architecture and performs fully optical analog computation with frequency‐domain parallel processing. An FPGA‐based error‐correction algorithm aims to
Tao Zhu +15 more
wiley +1 more source
Classified modeling and day-ahead optimal scheduling of multi-type adjustable industrial loads in industrial microgrid using improved approximate dynamic programming. [PDF]
Sun T +5 more
europepmc +1 more source

