A New Computational Approach to the Levenberg-Marquardt Learning Algorithm.

Jaroslaw Bilski,Barosz Kowalczyk,Jacek Smolag

ICAISC (1)（2022）

引用 0|浏览0

暂无评分

摘要

A new parallel computational approach to the Levenberg-Marquardt learning algorithm is presented. The proposed solution is based on the AVX instructions to effectively reduce the high computational load of this algorithm. Detailed parallel neural network computations are explicitly discussed. Additionally obtained acceleration is shown based on a few test problems.

查看译文

关键词

Neural network learning algorithm, Levenberg-marquardt learning algorithm, Vector computations, Approximation, Classification

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要