Artificial Intelligence News

RSS

AI Framework Improves Learning on Edge Devices

With FTTE, federated learning on edge devices becomes feasible, cutting training memory by 80% and communication load by 69% while ensuring rapid convergence.

4 May 2026

AI Discovery Pipeline Identifies Tuberculosis Drug Targets

Five novel inhibitors of the MenT3 toxin were identified through a machine learning and simulations pipeline, offering new avenues for tuberculosis treatment.

30 Apr 2026

Machine Learning Predicts Toxic Metal Levels in Marine Systems

Combining machine learning and feature selection, this research accurately predicts aluminum levels in marine environments, enhancing monitoring efficiency.

23 Apr 2026

Machine Learning Models Predict Stroke Risk in Atrial Fibrillation

Innovative machine learning models using routine clinical data offer superior stroke risk prediction in atrial fibrillation, enabling personalized patient care.

14 Apr 2026

AI Vibe Coding Transforms Modern Software Development

Vibe coding democratizes software creation, allowing users to turn ideas into functional prototypes with AI, prioritizing communication and critical thinking.

13 Apr 2026

Detecting IoT Malware in EV Chargers with Deep Learning

A new study presents a deep learning approach for IoT malware detection in EV charging stations, addressing key limitations and enhancing detection accuracy.

9 Apr 2026

$1.2m Partnership for Robots to Fix Roads

An AI-powered robotic system will soon detect and repair cracked roads thanks to a $1.2 million partnership between Charles Darwin University (CDU), Civiltech Solutions, and the Additive Manufacturing Cooperative Research Centre (AMCRC).

3 Apr 2026

Brain-Inspired Chip Could Make Some AI Tasks up to 2,000 Times More Energy Efficient, Study Finds

A new type of computer chip that uses the physics of materials to process information could make some artificial intelligence (AI) systems far more energy efficient, researchers have found.

3 Apr 2026

Better Uncertainty Quantification for Large Language Models

Improving uncertainty quantification in LLMs, this method combines epistemic and aleatoric uncertainty, leading to better error detection and model performance.

2 Apr 2026