粒子群优化提高神经网络训练精度及其分类稳定性分析
Accuracy Improvement of Neural Network Training using Particle Swarm Optimization and its Stability Analysis for Classification
摘要：
监督分类是当今场景中最活跃和新兴的研究趋势。因此，人工神经网络（ANN）技术得到了广泛的应用，并日益受到研究者的关注。ANN训练旨在找到诸如权重（$\textbf{W}$）和偏差（$b$）的参数的适当设置，以适当地对给定的数据样本进行分类。训练过程中制定的错误最小化问题，其中包括许多局部最优的搜索景观。本文提出了一种改进的粒子群优化算法，以最小化误差函数为目标，对真实数据集进行分类。一个稳定性分析，以建立所提出的方法，提高分类精度的效率。混淆矩阵、$F$ -测度和收敛图等性能指标表明，分类精度得到了显著提高。
英文摘要：
Supervised classification is the most active and emerging research trends in today's scenario. In this view, Artificial Neural Network (ANN) techniques have been widely employed and growing interest to the researchers day by day. ANN training aims to find the proper setting of parameters such as weights ($\textbf{W}$) and biases ($b$) to properly classify the given data samples. The training process is formulated in an error minimization problem which consists of many local optima in the search landscape. In this paper, an enhanced Particle Swarm Optimization is proposed to minimize the error function for classifying real-life data sets. A stability analysis is performed to establish the efficiency of the proposed method for improving classification accuracy. The performance measurement such as confusion matrix, $F$-measure and convergence graph indicates the significant improvement in the classification accuracy.
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。
