arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.07352cs.LG
收藏

基于数据分布的课程学习

Data Distribution-based Curriculum Learning

Shonal Chaudhry, Anuraganand Sharma

AI总结:

本文提出基于数据分布的课程学习方法DDCL,利用样本密度和欧几里得距离评分确定训练顺序,实验表明该方法提升了分类准确率并加快了收敛速度。

摘要:

训练样本的顺序对分类器的性能有显著影响。课程学习是一种将训练样本从易到难排序的方法。本文提出了一种名为基于数据分布的课程学习(DDCL)的新方法。DDCL利用数据集的数据分布来构建基于样本顺序的课程。使用两种评分方法DDCL (Density)和DDCL (Point)对训练样本进行评分,从而决定其训练顺序。DDCL (Density)使用样本密度分配分数,而DDCL (Point)利用欧几里得距离进行评分。我们通过在多个数据集上使用神经网络、支持向量机和随机森林分类器进行实验来评估所提出的DDCL方法。评估结果表明,与没有任何课程的标准评估相比,应用DDCL提高了所有数据集的平均分类准确率。此外,对单个训练周期的错误损失分析表明,与无课程方法相比,使用DDCL的收敛速度更快。

英文摘要:

The order of training samples can have a significant impact on the performance of a classifier. Curriculum learning is a method of ordering training samples from easy to hard. This paper proposes the novel idea of a curriculum learning approach called Data Distribution-based Curriculum Learning (DDCL). DDCL uses the data distribution of a dataset to build a curriculum based on the order of samples. Two types of scoring methods known as DDCL (Density) and DDCL (Point) are used to score training samples thus determining their training order. DDCL (Density) uses the sample density to assign scores while DDCL (Point) utilises the Euclidean distance for scoring. We evaluate the proposed DDCL approach by conducting experiments on multiple datasets using a neural network, support vector machine and random forest classifier. Evaluation results show that the application of DDCL improves the average classification accuracy for all datasets compared to standard evaluation without any curriculum. Moreover, analysis of the error losses for a single training epoch reveals that convergence is faster when using DDCL over the no curriculum method.

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。

↑