Faculty of Medicine, Catholic University of Leuven (KU Leuven), Leuven, Belgium.
Department of Engineering, Islamic Azad University, Tehran North Branch, Tehran, Iran.
J Healthc Eng. 2022 Mar 23;2022:4703682. doi: 10.1155/2022/4703682. eCollection 2022.
One of the leading algorithms and architectures in deep learning is Convolution Neural Network (CNN). It represents a unique method for image processing, object detection, and classification. CNN has shown to be an efficient approach in the machine learning and computer vision fields. CNN is composed of several filters accompanied by nonlinear functions and pooling layers. It enforces limitations on the weights and interconnections of the neural network to create a good structure for processing spatial and temporal distributed data. A CNN can restrain the numbering of free parameters of the network through its weight-sharing property. However, the training of CNNs is a challenging approach. Some optimization techniques have been recently employed to optimize CNN's weight and biases such as Ant Colony Optimization, Genetic, Harmony Search, and Simulated Annealing. This paper employs the well-known nature-inspired algorithm called Shuffled Frog-Leaping Algorithm (SFLA) for training a classical CNN structure (LeNet-5), which has not been experienced before. The training method is investigated by employing four different datasets. To verify the study, the results are compared with some of the most famous evolutionary trainers: Whale Optimization Algorithm (WO), Bacteria Swarm Foraging Optimization (BFSO), and Ant Colony Optimization (ACO). The outcomes demonstrate that the SFL technique considerably improves the performance of the original LeNet-5 although using this algorithm slightly increases the training computation time. The results also demonstrate that the suggested algorithm presents high accuracy in classification and approximation in its mechanism.
深度学习中的主要算法和架构之一是卷积神经网络 (CNN)。它代表了图像处理、目标检测和分类的独特方法。CNN 在机器学习和计算机视觉领域已被证明是一种有效的方法。CNN 由几个滤波器组成，伴随非线性函数和池化层。它对神经网络的权重和连接施加限制，以创建处理空间和时间分布数据的良好结构。CNN 通过其权重共享特性可以限制网络的自由参数数量。然而，CNN 的训练是一个具有挑战性的方法。最近采用了一些优化技术来优化 CNN 的权重和偏差，例如蚁群优化、遗传算法、和声搜索和模拟退火。本文采用了一种名为 Shuffled Frog-Leaping Algorithm (SFLA) 的著名自然启发式算法来训练经典的 CNN 结构（LeNet-5），这是以前没有经历过的。通过使用四个不同的数据集来研究训练方法。为了验证研究，将结果与一些最著名的进化训练器进行了比较：鲸鱼优化算法 (WO)、细菌群觅食优化算法 (BFSO) 和蚁群优化算法 (ACO)。结果表明，尽管使用该算法略微增加了训练计算时间，但 SFL 技术可以显著提高原始 LeNet-5 的性能。结果还表明，所提出的算法在其机制中具有高精度的分类和逼近能力。
