A new technical paper titled “Massively parallel and universal approximation of nonlinear functions using diffractive processors” was published by researchers at UCLA. “Nonlinear computation is ...

Researchers at the University of California, Los Angeles (UCLA) have developed an optical computing framework that performs large-scale nonlinear computations using linear materials. Reported in ...

Abstract: The affinity graph is regarded as a mathematical representation of the local manifold structure. The performance of locality-preserving projections (LPPs) and its variants is tied to the ...

Baptist Medical Center, Department of Behavioral Health, Jacksonville, FL, United States Introduction: This study investigates four subdomains of executive functioning—initiation, cognitive inhibition ...

STG-DMD (Sparse-Coded Time-Delay Graph Dynamic Mode Decomposition) is a data-driven framework for modeling nonlinear dynamics on graph structures. It integrates: StgDmd/ ├── code/ │ ├── artificial/ │ ...

Abstract: The distributed nonlinear adaptive graph filter (DNAGF) is developed with the single nonlinear graph filter model (NGFM) to handle streaming datasets. However, the current DNAGFs tend to ...

Recent work has established an alternative to traditional multi-layer perceptron neural networks in the form of Kolmogorov-Arnold Networks (KAN). The general KAN framework uses learnable activation ...

In-context learning (ICL) enables LLMs to adapt to new tasks by including a few examples directly in the input without updating their parameters. However, selecting appropriate in-context examples ...

Ames National Laboratory, U.S. Department of Energy, Ames, Iowa 50011, United States Department of Physics and Astronomy, Iowa State University, Ames, Iowa 50011, United States ...