首页|New Machine Learning Study Findings Recently Were Published by a Researcher at S an Diego State University (Exploring Downscaling in High-Dimensional Lorenz Mode ls Using the Transformer Decoder)
New Machine Learning Study Findings Recently Were Published by a Researcher at S an Diego State University (Exploring Downscaling in High-Dimensional Lorenz Mode ls Using the Transformer Decoder)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on artificial intelligenc e is the subject of a new report. According to news reporting from San Diego, Ca lifornia, by NewsRx journalists, research stated, “This paper investigates the f easibility of downscaling within high-dimensional Lorenz models through the use of machine learning (ML) techniques.” The news journalists obtained a quote from the research from San Diego State Uni versity: “This study integrates atmospheric sciences, nonlinear dynamics, and ma chine learning, focusing on using large-scale atmospheric data to predict small- scale phenomena through ML-based empirical models. The highdimensional generali zed Lorenz model (GLM) was utilized to generate chaotic data across multiple sca les, which was subsequently used to train three types of machine learning models : a linear regression model, a feedforward neural network (FFNN)-based model, an d a transformer-based model. The linear regression model uses large-scale variab les to predict small-scale variables, serving as a foundational approach. The FF NN and transformer-based models add complexity, incorporating multiple hidden la yers and selfattention mechanisms, respectively, to enhance prediction accuracy . All three models demonstrated robust performance, with correlation coefficient s between the predicted and actual small-scale variables exceeding 0.9.”
San Diego State UniversitySan DiegoC aliforniaUnited StatesNorth and Central AmericaCyborgsEmerging Technolog iesMachine Learning
NETL
NSTL
