arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.14558cs.LG
收藏

足球基础模型

A Foundation Model for Soccer

University of Toronto(多伦多大学)

Ethan Baron, Daniel Hocevar, Zach Salehe

AI总结:

提出一种基于变换器的足球基础模型,利用职业联赛数据预测比赛后续动作,并与马尔可夫模型和多层感知机比较性能,开源实现。

摘要:

我们提出了一种足球基础模型,该模型能够根据给定的动作序列预测足球比赛中的后续动作。作为概念验证,我们在一个职业足球联赛的三个赛季数据上训练了一个变换器架构。我们定量和定性地将该变换器架构的性能与两个基线模型进行了比较:马尔可夫模型和多层感知机。此外,我们讨论了该模型的潜在应用。我们在https://github.com/danielhocevar/Foundation-Model-for-Soccer提供了我们方法的开源实现。

英文摘要:

We propose a foundation model for soccer, which is able to predict subsequent actions in a soccer match from a given input sequence of actions. As a proof of concept, we train a transformer architecture on three seasons of data from a professional soccer league. We quantitatively and qualitatively compare the performance of this transformer architecture to two baseline models: a Markov model and a multi-layer perceptron. Additionally, we discuss potential applications of our model. We provide an open-source implementation of our methods at https://github.com/danielhocevar/Foundation-Model-for-Soccer.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑