Semiconductor Engineering

Parallel Implementation Of Nonlinear Functions Using An Optical Processor (UCLA)

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 ...
GitHub

Nonlinear Locality-Preserving Projections With Dynamic Graph Learning

This repo hosts the code for paper "Nonlinear Locality-Preserving Projections With Dynamic Graph Learning, in TNNLS-2025". The proposed method addresses two main limitations: first, the pre-designed ...
Semiconductor Engineering

Implementing AI Activation Functions

Activation functions play a critical role in AI inference, helping to ferret out nonlinear behaviors in AI models. This makes them an integral part of any neural network, but nonlinear functions can ...
IEEE

A Nonlinear Weighted Graph Convolution Network Based on Manifold Geometric Regularization for Hyperspectral Image Classification

Abstract: Extracting spatial–spectral joint features has become a critical approach for improving model classification performance in the field of hyperspectral image classification (HSIC). However, ...