Convolutional neural network (CNN) is one of the most frequently used deep learning techniques. Various forms of models have been proposed and im-proved for learning at CNN. When learning with CNN, it is necessary to determine the optimal hyperparameters. However, the number of hyperparameters is so large that it is difficult to do it manually, so much research has been done on automation. A method that uses metaheuristic algorithms is attracting attention in research on hyperparameter optimization. Metaheuristic algorithms are naturally inspired and include evolution strategies, genetic algorithms, antcolony optimization and particle swarm optimization. In particular, particle swarm optimization converges faster than genetic algorithms, and various models have been proposed. In this paper, we pro-pose CNN hyperparameter optimization with linearly decreasing weight particle swarm optimization (LDWPSO). In the experiment, the MNIST data set and CIFAR-10 data set, which are often used as benchmark data sets, are used. By opti-mizing CNN hyperparameters with LDWPSO, learning the MNIST and CIFAR-10 datasets, we compare the accuracy with a standard CNN based on LeNet-5. As a result, when using the MNIST dataset, the baseline CNN is 94.02% at the 5th epoch, compared to 98.95% for LDWPSO CNN, which improves accuracy. When using the CIFAR-10 dataset, the Baseline CNN is 28.07% at the 10th epoch, compared to 69.37% for the LDWPSO CNN, which greatly improves accuracy. This paper is presented at the 36th Annual Conference of the Japanese Society for Artificial In-telligence. The final version is available at the following URL: https://www.jst-age.jst.go.jp/article/pjsai/JSAI2022/0/JSAI2022_2S4IS2b03/_article/-char/en

翻译：卷积神经网络（CNN）是最常用的深度学习技术之一。针对CNN的学习，已有多种形式的模型被提出并改进。在使用CNN进行学习时，需要确定最优超参数。然而，超参数数量庞大，手动调整十分困难，因此大量研究致力于自动化超参数优化。在超参数优化研究中，利用元启发式算法的方法正受到关注。元启发式算法受自然启发，包括进化策略、遗传算法、蚁群优化和粒子群优化。其中，粒子群优化比遗传算法收敛更快，且已有多种变体被提出。本文提出一种采用线性递减权重粒子群优化（LDWPSO）的CNN超参数优化方法。实验中，使用了常用于基准数据集的MNIST数据集和CIFAR-10数据集。通过使用LDWPSO优化CNN超参数，在MNIST和CIFAR-10数据集上进行学习，并与基于LeNet-5的标准CNN进行精度对比。结果表明，使用MNIST数据集时，基线CNN在第5个epoch的精度为94.02%，而LDWPSO CNN为98.95%，精度得到提升。使用CIFAR-10数据集时，基线CNN在第10个epoch的精度为28.07%，而LDWPSO CNN为69.37%，精度大幅提升。本文发表于第36届日本人工智能学会年会。最终版本可通过以下URL获取：https://www.jstage.jst.go.jp/article/pjsai/JSAI2022/0/JSAI2022_2S4IS2b03/_article/-char/en