Weekly Newsletter
Excepteur sint occaecat cupidatat non proident
neural
AI model based on neural oscillations delivers stable, efficient long-sequence predictions
Schematic drawing of the proposed Linear Oscillatory State-Space model (LinOSS). Credit: arXiv (2024). DOI: 10.48550/arxiv.2410.03943 Researchers from MIT’s Computer Science and Artificial Intelligence...
Lovabledaniels
Novel out-of-core mechanism introduced for large-scale graph neural network training
Schematic Diagram: Capsule System Workflow Framework. Credit: Image by USTC A research team has introduced a new out-of-core mechanism, Capsule, for large-scale GNN...
Lovabledaniels
Neural network learns to hesitate for improved accuracy
Credit: Pixabay/CC0 Public Domain Researchers from the Skoltech AI Center, together with colleagues from the Institute for Information Transmission Problems of the Russian...
Lovabledaniels
Neural networks can recognize production processes by video to enhance industrial safety and efficiency
Collected processes examples. Credit: IEEE Access (2025). DOI: 10.1109/ACCESS.2025.3545768 A research team from the Skoltech AI Center and Samara University have developed a...
Lovabledaniels
Combining photonic neural networks with distributed acoustic sensing for infrastructure monitoring
By directly leveraging light signals received from distributed acoustic sensing systems, the proposed photonic neural network architecture provides massive gains in accuracy and...
Lovabledaniels
Researchers teach neural networks to add clouds and snow to images
Credit: Unsplash/CC0 Public Domain Nikita Belyakov and Svetlana Illarionova, researchers from the Skoltech AI Center, presented a new method for semantic segmentation of...
Lovabledaniels
One-step 3D microelectrode technology for neural interfaces developed
Pusan National University researchers developed a novel microelectrothermoforming (μETF) technique to fabricate flexible microelectrode arrays (MEAs) with 3D structures. This one-step process improves...
Lovabledaniels
Dual-domain architecture shows almost 40 times higher energy efficiency for running neural networks
AnDi hybrid computing system for complex FP-based regression neural network inference. Credit: Ze Wang, Tsinghua University. Many conventional computer architectures are ill-equipped to...
Lovabledaniels
Neural network cuts cost of engineering simulations
An example of TEECNet model structure with 3 hidden layers and hidden layer dimension of 32. Credit: Journal of Computational Physics (2024). DOI:...
Lovabledaniels
