IEEE

Compressing Quaternion Convolutional Neural Networks for Audio Classification

Abstract: Conventional Convolutional Neural Networks (CNNs) in the real domain have been widely used for audio classification. However, CNNs have limited ability to capture correlations across ...
PNAS

Convolutional neural networks outperform other presence-only species distribution modeling ...

Species distribution models (SDMs) often overlook critical spatial heterogeneity and multiscale environmental patterns, which limit their predictive accuracy for species occurrences. We demonstrate ...
Frontiers

A vision-based drowsiness detection system for railway operators using lightweight ...

This research addresses the challenge of monitoring railway driver drowsiness using a real-time, vision-based system powered by convolutional neural networks, specifically the YOLOv8 architecture ...
The New York Times

Ex-Employee Sentenced to 4 Years for Sabotaging Company’s Computer Network

The man, a former software developer for Eaton Corporation, wrote malicious code that crashed servers on the company’s network in 2019, prosecutors said. By Hannah Ziegler A former software developer ...
IEEE

Quaternion Convolutional Neural Networks for Image Classification

Abstract: In recent years, real-valued neural networks have made significant progress in computer vision tasks such as image classification, object detection, and semantic segmentation. However, ...