To address the issues of the impact of hyperparameters on the performance of convolution-al neural network(CNN)in various tasks,and to overcome the limited precision of traditional may-fly optimization algorithm(MOA),a hyperparameter optimization method of CNN via multi-strategy improved MOA is proposed.First,population initialization is enhanced by separately initializing the male and female populations using the theory of good point set and the Tent mapping strategy,ensur-ing a more uniform and diverse distribution of the population.Second,a nonlinear dynamic speed regulation strategy is studied,which non-linearly improves the gravitational coefficient and positive attraction coefficient in the velocity update of the mayfly algorithm weight strategy is used to update the ephemera position,and a multi-strategy improved MOA algorithm is constructed to meet the re-quirements of the search ability,convergence speed and accuracy of the MOA.Finally,the multi-strategy improved MOA is applied into the CNN model to design a hyperparameter optimization al-gorithm,aiming at enhancing the overall classification performance of the CNN.Experimental re-sults conducted on seven benchmark functions demonstrated the effectiveness of the improved may-fly optimization algorithm.Furthermore,classification experiments are conducted on the MNIST and Fashion-MNIST datasets.The experimental results indicated that the developed algorithm can effec-tively enhance the recall rate and accuracy of the CNN model,exhibiting strong generalization capa-bility.
mayfly optimizationgood point settent mappingconvolutional neural network
维普
万方数据
