neural networks News and Research

RSS

PNNL Scientists Build Trustworthy AI That Knows Its Limits in Materials Discovery

Researchers at Pacific Northwest National Laboratory have developed a method to measure how well AI models, specifically neural network potentials, are trained to predict material properties. The approach quantifies uncertainty to enhance model trust and identifies areas where additional training is required.

25 Apr 2025

Penn Engineers Unleash Programmable Photonic Chip That Trains AI at the Speed of Light

Penn Engineers have unveiled the first programmable chip capable of training nonlinear neural networks using only light, revolutionizing photonic AI. This innovation promises rapid, energy-efficient AI training and marks a significant step toward fully light-powered computing.

16 Apr 2025

AI-Powered Nanophotonics Revolutionizes Computing and Sensing for a Smarter Future

This paper reviews the convergence of artificial intelligence and nanophotonics, highlighting how optical neural networks and metasurfaces are revolutionizing fast, energy-efficient computing and advanced sensing. The authors analyze current challenges and future opportunities for integrating intelligent photonics into real-world AI technologies.

16 Apr 2025

AI Predicts Nuclear Reactor Failures 1,400 Times Faster With Virtual Sensors

Researchers at the University of Illinois Urbana-Champaign developed a deep-learning tool that acts as a virtual sensor, predicting critical conditions in nuclear reactors up to 1,400 times faster than traditional simulations. This AI-driven approach improves safety by enabling real-time system monitoring.

14 Apr 2025

New AI Method Boosts Accuracy By Learning From Incomplete Data

Researchers developed LR-GCN, an AI method that improves decision-making by identifying hidden patterns in incomplete data. It boosts predictive accuracy by up to 17%, making AI systems more reliable across real-world applications.

10 Apr 2025

AI Slashes Ocean Simulation Time While Preserving Accuracy

Researchers at Osaka Metropolitan University developed a machine learning-powered fluid simulation model that slashes computation time from 45 minutes to 3 minutes. Using graph neural networks, their model retains high accuracy across diverse fluid behaviors, aiding ocean energy and ship design.

3 Apr 2025

NdLinear Reinvents Neural Layers To Boost Accuracy And Slash Parameters In AI Models

A new study proposes NdLinear, a multi-dimensional linear layer that preserves data structure and slashes parameter counts across neural networks — from CNNs to Transformers. It outperforms standard layers in accuracy, efficiency, and scalability.

24 Mar 2025

New Memristor Mimics Brain Function to Prevent AI From Forgetting

Researchers from Jülich have developed a robust new memristor that mimics brain-like learning and memory. Its novel switching mechanism could overcome the “catastrophic forgetting” problem in neural networks.

21 Mar 2025

Researchers Cut AI Energy Use by 90% with Smarter, Leaner Models

Researchers at Saarland University and the German Research Center for Artificial Intelligence have developed techniques to reduce AI energy consumption by up to 90%, making AI models smaller, more efficient, and more accessible to businesses. Their approach, showcased at Hannover Messe, aims to revolutionize sustainable AI.

19 Mar 2025

AI-Powered Vision System Enables Safe Autonomous Aircraft Landings in Emergencies

Researchers have developed a monocular vision-based system that enables autonomous aircraft to identify and land safely in unknown environments, improving emergency response and flight safety.

18 Mar 2025

Why AI Needs Better Data Systems to Reach Its Full Potential

Researchers from the Chinese Academy of Sciences emphasize the urgent need to align AI data systems with the complex, multi-level nature of scientific data to improve AI performance and reliability. They call for global standards and frameworks to structure data properly and foster AI's healthy development.

11 Mar 2025

Los Alamos AI Breakthrough Neutralizes Adversarial Attacks and Restores Trust in Neural Networks

...

11 Mar 2025

Meet DIDACT: The AI System That Learns and Improves Scientific Computing Daily

Researchers at Jefferson Lab developed an AI-based system, DIDACT, to optimize high-performance computing clusters by continually learning and selecting the best-performing model daily, reducing system downtime and costs.

3 Mar 2025

New AI Lets Robots Develop Self-Knowledge and Adapt Like Living Beings

Columbia Engineering researchers have enabled robots to develop "kinematic self-awareness" by watching their own movements through a single camera, allowing them to self-model, adapt to damage, and learn new skills without human intervention.

26 Feb 2025

Scientists Uncover How Hidden Interactions Shape Complex Networks

Researchers highlight the limitations of classical networks in capturing complex multi-agent interactions, proposing higher-order structures like simplicial complexes and hypergraphs to model real-world systems more effectively.

19 Feb 2025

AI Breakthrough: Synaptic Device Array Achieves Human-Like Visual Processing

Researchers have developed a 28×28 synaptic device array that mimics the human visual system, achieving 96.5% digit recognition accuracy and paving the way for advanced neuromorphic artificial vision.

18 Feb 2025

Students Build Beginner-Friendly Machine Learning Guide to Combat Antibiotic Resistance

San Francisco State University researchers created a step-by-step machine-learning tutorial to predict antibiotic resistance, making complex concepts accessible to beginners in biology and health sciences.

11 Feb 2025

Torque Clustering Revolutionizes AI by Mimicking Natural Intelligence

Researchers have developed Torque Clustering, a new AI algorithm that mimics natural intelligence, enabling unsupervised learning with unprecedented accuracy and efficiency.