Loss functions and constraints improve sea surface height prediction

In order to understand currents, tides and other ocean dynamics, scientists need to accurately capture sea surface height, or ...
Quanta Magazine

Using AI, Mathematicians Find Hidden Glitches in Fluid Equations

A $1 million prize awaits anyone who can show where the math of fluid flow breaks down. With specially trained AI systems, ...
IEEE

Directed Graph Topology Preservation in Multi-Robot Systems With Limited Field of View Using Control Barrier Functions

Abstract: This paper addresses the crucial challenge of maintaining the directed graph topology in multi-robot systems, particularly when operating under limited field-of-view constraints and with a ...
Simon Fraser University

Calculating Principal Components

Principal component analysis summarizes high dimensional data into a few dimensions. Each dimension is called a principal component and represents a linear combination of the variables. The first ...
GitHub

Spatio-temporal Fusion Flow with Dynamic Graph Leaning for Unsupervised Multivariate Time Series Anomaly Detection

Detecting anomalies in multivariate time series (MTS) is essential for maintaining system safety in industrial environments. Due to the challenges associated with acquiring labeled data, unsupervised ...
IEEE

Graph Neural Network-Enhanced Multivariate Time Series Forecasting with Series-Core Fusion

Abstract: This study introduces Starformer, a hybrid model combining Graph Neural Networks (GNNs) with a novel Series-Core Fusion (SC-Fusion) mechanism for urban traffic prediction. By leveraging GNNs ...
GitHub

Mathematics of Machine Learning

Mathematics of Machine Learning provides a rigorous yet accessible introduction to the mathematical underpinnings of machine learning, designed for engineers, developers, and data scientists ready to ...