Accuracy Improvement of Neural Network Training using Particle Swarm Optimization and its Stability Analysis for Classification
This work addresses the challenge of improving classification accuracy in neural networks for real-life datasets, representing an incremental advancement in optimization techniques.
The paper tackled the problem of local optima in neural network training for classification by proposing an enhanced Particle Swarm Optimization method to minimize error, resulting in significant improvements in classification accuracy as measured by metrics like confusion matrix and F-measure.
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.