arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.09983cs.LGcs.AI
收藏

利用自然启发算法优化神经网络权值

Optimizing Neural Network Weights using Nature-Inspired Algorithms

University of Regina(里贾纳大学)

Wael Korani, Malek Mouhoub, Samira Sadaoui

摘要:

本研究旨在使用自然启发的优化算法优化深度前馈神经网络(DFNN)训练,如PSO,MTO及其变体MTOCL。我们展示了这些算法在从数据中学习时如何有效地更新DFNN的权重。我们使用三个威斯康星州的乳腺癌数据集,原始,诊断和预后,在不同的实验方案下,DFNN融合优化算法的性能进行评估。实证分析表明,MTOCL是最好的表现在大多数情况下,在三个数据集。此外,MTOCL与过去的原始数据集的权重优化算法相当,并且优于其他数据集,特别是对于具有挑战性的预后数据集。

英文摘要:

This study aims to optimize Deep Feedforward Neural Networks (DFNNs) training using nature-inspired optimization algorithms, such as PSO, MTO, and its variant called MTOCL. We show how these algorithms efficiently update the weights of DFNNs when learning from data. We evaluate the performance of DFNN fused with optimization algorithms using three Wisconsin breast cancer datasets, Original, Diagnostic, and Prognosis, under different experimental scenarios. The empirical analysis demonstrates that MTOCL is the most performing in most scenarios across the three datasets. Also, MTOCL is comparable to past weight optimization algorithms for the original dataset, and superior for the other datasets, especially for the challenging Prognostic dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑