Evaluation of AdaBoost's elastic net-type regularized multi-core learning algorithm in volleyball teaching actions

Volleyball teaching is one of the traditional contents of physical education in our country. It plays an extremely important role in improving students' volleyball skills, promoting their physical and mental health, and improving their character training. However, due to the influence of volleyball's own characteristics and the restriction of test-oriented education concepts, the development of volleyball teaching has been seriously lagging. It not only fails to effectively adapt to the social development situation, but also severely weakens the students' athletic ability, making volleyball learn from the students. The interest in volleyball has gradually decreased, and the audience who watched the volleyball game has also been reduced. In addition, the degree of attention has also been declining, which ultimately makes volleyball teaching a more embarrassing and marginalized situation. This article uses the method of literature review to illustrate the innovative significance of the volleyball teaching evaluation system, and discuss its related innovative development methods. Its purpose is to correct the shortcomings of the traditional teaching evaluation system, improve the effectiveness of volleyball teaching evaluation, and stimulate students to learn volleyball. Interest also builds self-confidence in learning, and provides necessary reference and reference. It is well known that selecting all kernel functions through a model that is not sparse will generate a lot of messy and unordered information and be sensitive to noise. In order to solve the above problems, this article will propose a very formal sequential learning algorithm based on the AdaBoost framework. When the basic classifier is selected iteratively, the proportion of the kernel function will be constrained by the elastic net type normalization, which is the mixed L norm and L. The norm constraint is to construct a basic classifier with the best combination of multiple basic cores, and in addition to receiving them into a powerful classifier.