Convolutional neural networks (CNNs) are widely used in image recognition. Numerous CNN models, such as LeNet, AlexNet, VGG, ResNet, and GoogLeNet, have been proposed by increasing the number of layers, to improve the performance of CNNs. However, performance deteriorates beyond a certain number of layers. Hence, hyperparameter optimisation is a more efficient way to improve CNNs. To validate this concept, a new algorithm based on simplified swarm optimisation is proposed to optimise the hyperparameters of the simplest CNN model, which is LeNet. The results of experiments conducted on the MNIST, Fashion MNIST, and Cifar10 datasets showed that the accuracy of the proposed algorithm is higher than the original LeNet model and PSO-LeNet and that it has a high potential to be extended to more complicated models, such as AlexNet.
翻译:革命神经网络(CNNs)被广泛用于图像识别。许多CNN模型,如LeNet、AlexNet、VGG、ResNet和GoogLeNet,都是通过增加层数来提出来提高CNN的性能的。但是,性能在一定的层数之外恶化。因此,超光谱优化是改进CNN的更有效方法。为了验证这个概念,建议采用基于简化的温和优化的新算法优化最简单的CNN模型的超参数,即LeNet。在MNIST、Fashion MNIST和Cifar10数据集上进行的实验结果表明,提议的算法的准确性高于原始的LeNet模型和PSO-LeNet, 并且它有很大潜力可以扩大到更复杂的模型,如AlexNet。