Singidunum University, Danijelova 32, 11000, Belgrade, Serbia.
Artificial Intelligence Engineering Department, Research Center for AI and IoT, AI and Robotics Institute, Near East University, Mersin 10, Turkey.
Sci Rep. 2022 Apr 15;12(1):6302. doi: 10.1038/s41598-022-09744-2.
Deep learning has recently been utilized with great success in a large number of diverse application domains, such as visual and face recognition, natural language processing, speech recognition, and handwriting identification. Convolutional neural networks, that belong to the deep learning models, are a subtype of artificial neural networks, which are inspired by the complex structure of the human brain and are often used for image classification tasks. One of the biggest challenges in all deep neural networks is the overfitting issue, which happens when the model performs well on the training data, but fails to make accurate predictions for the new data that is fed into the model. Several regularization methods have been introduced to prevent the overfitting problem. In the research presented in this manuscript, the overfitting challenge was tackled by selecting a proper value for the regularization parameter dropout by utilizing a swarm intelligence approach. Notwithstanding that the swarm algorithms have already been successfully applied to this domain, according to the available literature survey, their potential is still not fully investigated. Finding the optimal value of dropout is a challenging and time-consuming task if it is performed manually. Therefore, this research proposes an automated framework based on the hybridized sine cosine algorithm for tackling this major deep learning issue. The first experiment was conducted over four benchmark datasets: MNIST, CIFAR10, Semeion, and UPS, while the second experiment was performed on the brain tumor magnetic resonance imaging classification task. The obtained experimental results are compared to those generated by several similar approaches. The overall experimental results indicate that the proposed method outperforms other state-of-the-art methods included in the comparative analysis in terms of classification error and accuracy.
深度学习最近在许多不同的应用领域取得了巨大的成功，例如视觉和人脸识别、自然语言处理、语音识别和手写识别。卷积神经网络是深度学习模型的一个子类，它是受人类大脑复杂结构启发而设计的，通常用于图像分类任务。所有深度神经网络中最大的挑战之一是过拟合问题，即模型在训练数据上表现良好，但在输入模型的新数据上无法做出准确的预测。已经引入了几种正则化方法来防止过拟合问题。在本手稿中呈现的研究中，通过利用群体智能方法选择适当的正则化参数 dropout 值来解决过拟合挑战。尽管群智能算法已经成功应用于该领域，但根据现有文献调查，它们的潜力尚未得到充分研究。如果手动执行，找到 dropout 的最佳值是一项具有挑战性和耗时的任务。因此，本研究提出了一种基于混合正弦余弦算法的自动化框架来解决这个主要的深度学习问题。第一个实验在四个基准数据集上进行：MNIST、CIFAR10、Semeion 和 UPS，第二个实验在脑肿瘤磁共振成像分类任务上进行。将获得的实验结果与其他几个类似方法生成的结果进行了比较。总体实验结果表明，在所比较的分析中，该方法在分类误差和准确性方面优于包括在内的其他最先进的方法。
