首页 | 本学科首页   官方微博 | 高级检索  
检索        

基于混合判别受限波兹曼机的音乐自动标注算法
引用本文:王诗俊,陈宁.基于混合判别受限波兹曼机的音乐自动标注算法[J].医学教育探索,2017,43(4):540-545.
作者姓名:王诗俊  陈宁
作者单位:华东理工大学信息科学与工程学院, 上海 200237,华东理工大学信息科学与工程学院, 上海 200237
基金项目:国家自然科学基金(61271349)
摘    要:对于音乐自动标注任务,在很多情况下,未标注的歌曲量远远超过已标注的歌曲数据,从而导致训练结果不理想。生成模型能够在某种程度上适应少量数据集的情况,得出较为满意的结果,然而,在有充分数据集的情况下生成模型的效果却劣于判别模型。本文提出了一种结合生成模型与判别模型两者优势的面向音乐自动标注的混合判别波兹曼机模型,该模型可明显提升音乐自动标注的准确率。实验结果表明,混合波兹曼机的效果不仅好于传统的机器学习模型,同时,模型在拥有足够训练数据量的情况下与判别模型效果相当,且在训练集较少的情况下效果也好于判别模型。另外,为了防止模型过拟合,还引入了Dropout规则化方法以进一步加强模型的性能。

关 键 词:音乐自动标注  混合判别受限波兹曼机  机器学习  人工智能
收稿时间:2016/9/28 0:00:00

Annotating Music with Hybrid Discriminative Restricted Boltzmann Machines
WANG Shi-jun and CHEN Ning.Annotating Music with Hybrid Discriminative Restricted Boltzmann Machines[J].Researches in Medical Education,2017,43(4):540-545.
Authors:WANG Shi-jun and CHEN Ning
Institution:School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China and School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
Abstract:For the music annotation,the amount of unlabeled music data is often much more than the labeled ones such that the training results are usually unsatisfying.Although generation model can be suitable for the smaller training data case to some extent and get higher quality results,it may be inferior to the discriminative model in the case of sufficient training data.By combining the advantages of the generation model and the discriminative model,this paper presents a hybrid discriminative restricted Boltzmann machines.The proposed hybrid model can improve the accuracy of the music annotation tasks.The experiment results show that the hybrid model is much better than the traditional machine learning models.Moreover,it is also better than the single discriminative Boltzmann machines for the case that the amount of training data is small and can attain the similar performance to the discriminative model in the case that the amount of training data is sufficient.Besides,the Dropout method is introduced in this paper to improve the model and prevent the overfitting for the smaller training data.
Keywords:annotating music  hybrid discriminative restricted Boltzmann machines  machine learning  artificial intelligence
点击此处可从《医学教育探索》浏览原始摘要信息
点击此处可从《医学教育探索》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号