Nature

AI models ‘subliminally’ transmit biases when training other systems

Using artificial-intelligence to teach other models can be cheaper and faster than building them from scratch, but this ...

Quantum simulations tackle photon polarization flip, but today's hardware falls short

For the last 80 years, the theory of quantum electrodynamics (QED), which describes all electromagnetic interactions, has ...
IEEE

Gaussian Process Based Learning Model Predictive Control With Application to USV

Abstract: This article presents a learning model predictive control (LMPC) method for nonlinear systems with additive state-dependent uncertainties. Both the residual part of the system and the ...
IEEE

A Gaussian Process Regression Method to Nowcast Cloud-to-Ground Lightning From Remote Sensing and Numerical Weather Modeling Data

Abstract: The climate change of the last decades is causing an increase in the frequency of extreme event occurrences. Numerous studies confirm the link between extreme meteorological events and ...
Frontiers

NeuralVisionNet: a probabilistic neural process model for continuous visual anticipation

The ability to anticipate future events continuously is a hallmark of biological vision, yet standard deep learning models often struggle with long-term coherence due to the rigid discretization of ...