Random Regrouping and Factorization in Cooperative Particle Swarm Optimization Based Large-Scale Neural Network Training

Dennis, Cody; Ombuki-Berman, Beatrice M.; Engelbrecht, Andries P.

doi:10.1007/s11063-019-10112-x

Cited by 2 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ese two studies give a relatively comprehensive overview of the main factors affecting the quality of physical education teaching, but the identified influencing factors are slightly broader and detached from the most direct influencing factors affecting the classroom itself [8]. In terms of the human element, it is mainly teachers and students; in terms of the physical element, the analysis mainly refers to the things associated with physical education, mainly involving specific hardware facilities; in terms of the physical element, it mainly refers to the things closely related to physical education classroom teachings, such as the writing of physical education lesson plans, the arrangement of physical education teaching tasks, the classroom teaching evaluation, and the avoidance of teaching safety hazards that exist in the classroom [9]. e influences identified in this study are relatively comprehensive and closely related to the classroom itself, but the analysis of each level is relatively simple while remaining slightly broad in scope.…”

Section: Introductionmentioning

confidence: 99%

A Model for Analyzing Teaching Quality Data of Sports Faculties Based on Particle Swarm Optimization Neural Network

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In this paper, we use a particle swarm optimization neural network algorithm to analyze the teaching data of physical education faculties and evaluate the quality of teaching in physical education faculties. By studying and analyzing the optimization problem of the weight parameters of convolutional neural network training, this paper designs a hybrid algorithm combining the improved PSO algorithm and the traditional gradient descent in the framework of the BP algorithm by using the gradient information of the loss function and the principle of group cooperative search through PSO algorithm. The hybrid algorithm takes the loss function as the objective function, based on the principle of the PSO algorithm, and optimizes the objective function by combining the gradient information of the loss function of the convolutional neural network. The convergence speed and global search ability of the algorithm are effectively improved while ensuring an acceptable increase in computation. The weight values of the three-level indicators of teacher teaching behavior, student learning behavior, and teaching environment relative to the teaching quality of physical education classroom are 0.106, 0.634, and 0.260, respectively, which shows that the dimension of student learning behavior has the highest weight value in the evaluation of physical education classroom teaching quality, followed by teaching environment and finally teacher teaching behavior. Teachers’ teaching ability will affect the effect of teaching methods, and the stronger the teaching ability is, the better the selection and utilization of teaching methods can be optimized.

show abstract

Section: Introductionmentioning

confidence: 99%

A Model for Analyzing Teaching Quality Data of Sports Faculties Based on Particle Swarm Optimization Neural Network

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

Particle swarm optimization neural network for research on artificial intelligence college English classroom teaching framework

Dong¹,

Wei²

2021

IFS

View full text Add to dashboard Cite

This paper based on the algorithm of particle swarm optimization neural network, the university English classroom training framework with artificial intelligence is researched and designed, and a personalized learning path based on an improved binary particle swarm algorithm based on the non-linear increase of inertial weights and the exploration of unknown space is proposed. The recommendation method improves the algorithm’s convergence speed and convergence accuracy. It is easy to jump out of the local optimum through the improvement of the algorithm, thereby solving the problem of low recommendation accuracy of the personalized learning path and improving the recommendation efficiency. To verify the recommended effect of the model and algorithm, this paper designs a simulation experiment and a learning platform that take the college English course as an example to verify the running performance and practical application effect of the proposed method. The above experiments show that the proposed method can improve the matching degree of the personalized learning path and the needs of learners, and improve the accuracy of application in personalized learning path recommendation.

show abstract

Random Regrouping and Factorization in Cooperative Particle Swarm Optimization Based Large-Scale Neural Network Training

Cited by 2 publications

References 44 publications

A Model for Analyzing Teaching Quality Data of Sports Faculties Based on Particle Swarm Optimization Neural Network

A Model for Analyzing Teaching Quality Data of Sports Faculties Based on Particle Swarm Optimization Neural Network

Particle swarm optimization neural network for research on artificial intelligence college English classroom teaching framework

Contact Info

Product

Resources

About