Fast AI for satellite learns to quantify uncertainty

Accurately tracking atmospheric greenhouse gases requires not only fast predictions but also reliable estimates of uncertainty. Researchers have developed a lightweight machine learning framework that ...

AI algorithm enables tracking of brainstem's vital white matter pathways

The signals that drive many of the brain and body's most essential functions—consciousness, sleep, breathing, heart rate and ...
Microsoft

Probabilistic Neural Architecture Search

In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of recent approaches, ...
Frontiers

Editorial: Neural network models in autonomous robotics

The integration of neural network models in autonomous robotics represents a monumental leap in artificial intelligence and robotics. These models, mirroring the human brain's complexity and ...
IEEE

Effective Probabilistic Neural Networks Model for Model-Based Reinforcement Learning USV

Abstract: Gaussian process (GP) offers a robust solution for modeling the dynamics of unmanned surface vehicles (USV) in model-based reinforcement learning (MBRL). However, the rapidly increasing ...
GitHub

Official Implementation of Sparsity Evolutionary Fokker-Planck-Kolmogorov Equation (ICLR 2025)

What is SFPK? This repo contains the pre-release implementation of Sparsity Evolutionary Fokker-Planck-Kolmogorov Equation pruner (SFPK-pruner), a novel probabilistic neural network pruner proposed in ...
IEEE

Probabilistic Neural Networks (PNNs) for Modeling Aleatoric Uncertainty in Scientific Machine Learning

Abstract: This paper investigates the use of probabilistic neural networks (PNNs) to model aleatoric uncertainty, which refers to the inherent variability in the input-output relationships of a system ...
Oak Ridge National Lab

Probabilistic neural networks for improved analyses with phenomenological R-matrix

We present a method for measurement analyses based on probabilistic deep neural networks that provide several advantages over conventional analyses with phenomenological models. These include ...
Wired

Liquid AI Is Redesigning the Neural Network

Artificial intelligence might now be solving advanced math, performing complex reasoning, and even using personal computers, but today’s algorithms could still learn a thing or two from microscopic ...
The New York Times

California Passes Law Protecting Consumer Brain Data

The state extended its current personal privacy law to include the neural data increasingly coveted by technology companies. By Jonathan Moens On Saturday, Governor Gavin Newsom of California signed a ...
MIT Technology Review

A new way to build neural networks could make AI more understandable

The simplified approach makes it easier to see how neural networks produce the outputs they do. A tweak to the way artificial neurons work in neural networks could make AIs easier to decipher.