论文标题
使用线性减小的重量粒子群优化优化卷积神经网络
Optimization of Convolutional Neural Network Using the Linearly Decreasing Weight Particle Swarm Optimization
论文作者
论文摘要
卷积神经网络（CNN）是最常用的深度学习技术之一。已经提出了各种形式的模型，并在CNN学习。使用CNN学习时，有必要确定最佳的超参数。但是，超参数的数量是如此之大，以至于很难手动进行，因此对自动化进行了很多研究。一种使用元启发式算法的方法引起了对超参数优化的研究的关注。元硫素算法是自然启发的，包括进化策略，遗传算法，抗殖民地优化和粒子群优化。特别是，粒子群优化比遗传算法更快，并且已经提出了各种模型。在本文中，我们以线性降低权重粒子群优化（LDWPSO）来促进CNN高参数优化。在实验中，使用通常使用的MNIST数据集和CIFAR-10数据集，通常用作基准数据集。通过使用LDWPSO进行Opti启用CNN超参数，学习MNIST和CIFAR-10数据集，我们将精度与基于LENET-5的标准CNN进行比较。结果，当使用MNIST数据集时，基线CNN在第5个时期为94.02％，而LDWPSO CNN为98.95％，这提高了准确性。当使用CIFAR-10数据集时，基线CNN在第10个时期为28.07％，而LDWPSO CNN为69.37％，这大大提高了准确性。本文在日本人工诉讼学会的第36届年度会议上发表。最终版本可在以下URL上找到：https：//doi.org/10.11517/pjsai.jsai.jsai2022.0_2s4is2b03
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://doi.org/10.11517/pjsai.JSAI2022.0_2S4IS2b03
