Physics World

Neural networks discover unstable singularities in fluid systems

The Navier–Stokes partial differential equation was developed in the early 19th century by Claude-Louis Navier and George Stokes. It has proved its worth for modelling incompressible fluids in ...
Science Daily

Training algorithm breaks barriers to deep physical neural networks

Researchers have developed an algorithm to train an analog neural network just as accurately as a digital one, enabling the development of more efficient alternatives to power-hungry deep learning ...
Risk.net

Robust financial calibration: a Bayesian approach for neural stochastic differential equations

This paper offers a Bayesian framework for the calibration of financial models using neural stochastic differential equations ...

ZAC Cognitive Explainable-AI for Situational Awareness recognized as far superior algorithm to achieve Self-Driving Level-5 than Neural Nets

Z Advanced Computing, Inc. (ZAC), the pioneer CognitiveExplainable-AI (Artificial Intelligence) (Cognitive XAI or CXAI) software startup, has been recognized as far superior to the current algorithms ...
CERN Courier

Neural networks boost B-tagging

The LHCb collaboration developed an inclusive deep-learning flavour tagger for neutral B-mesons, improving tagging power by ...

WiMi Studies Hybrid Quantum-Classical Convolutional Neural Network Model

(NASDAQ: WiMi) ("WiMi" or the "Company"), a leading global Hologram Augmented Reality ("AR") Technology provider, today announced that they are actively exploring a shallow hybrid quantum-classical ...