IEEE

IntegralCAM: Integral-based contribution estimation and visualization for convolutional neural networks

To explain how a convolutional neural network (CNN) processes an image, it is common to generate classification activation maps (CAMs) to reveal image areas that are relevant to output. Nevertheless, ...
IEEE

Graph-Based Visualization and Fault Diagnosis in Large-Scale Industrial Sensor Networks Using KNN-Constructed Graph Neural Networks(GNN)-A Approach Synthetic Dataset

Abstract: In this study, we present a scalable method for modeling and visualizing large-scale industrial sensor networks using Graph Neural Network (GNN) principles. By applying the K-Nearest ...
The University of Texas at Arlington

UTA researcher uses AI to rethink navigation skills

While the findings point to limits in what AI can currently reveal about everyday cognitive skills, the technology remains a powerful research tool. Weisberg said more robust models could detect ...
eLife

Adjoint propagation of error signal through modular recurrent neural networks for biologically plausible learning

Biologically plausible learning mechanisms have implications for understanding brain functions and engineering intelligent systems. Inspired by the multi-scale recurrent connectivity in the brain, we ...