权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Research of Sequential Multitask Learning and ItsApplication to Patlern Recognition

顺序多任务学习及其在模式识别中的应用研究

基本信息

批准号：
18500174
负责人：
OZAWA Seiichi
金额：
$ 2.63万
依托单位：
Kobe University
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (C)
财政年份：
2006
资助国家：
日本
起止时间：
2006 至 2007
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-18500174/
关键词：
Machine Learning Multitask Learning Neural Networks Incremental Learning Pattern Recognition Principal Component Analysis Features Extraction Kernel Method

项目摘要

This research project developed a new learning algorithm for the multi-task pattern recognition problem. This project considers learning multiple classification tasks online where no information is ever provided about the task category of a training example. The algorithm thus needs an automated task recognition capability to properly learn the different classification tasks. The learning mode is “online" where training examples for different tasks are mixed in a random fashion and given sequentially one after another. It is assumed that the classification tasks are related to each other and that their training examples appear in random sequences during “online training." Thus, the learning algorithm has to continually switch from learning one task to another whenever the training examples change to a different task. This also implies that the learning algorithm has to detect task changes automatically and fast and utilize knowledge of previous tasks to learn new tasks. Overall, automated task recognition falls in the category of unsupervised learning since no information about task categories of training examples is provided to the algorithm. The performance of the algorithm is evaluated using several artificially generated and three UCI datasets. The experiments in this project verify that the proposed algorithm can indeed acquire and accumulate task knowledge and that the transfer of knowledge from tasks already learned enhances the speed of knowledge acquisition on new tasks.

本研究针对多任务模式识别问题，提出一种新的学习算法。该项目考虑在线学习多个分类任务，其中没有提供关于训练示例的任务类别的信息。因此，该算法需要自动任务识别能力，以正确地学习不同的分类任务。学习模式是“在线”的，其中不同任务的训练示例以随机方式混合并依次给出。假设分类任务彼此相关，并且它们的训练样本在“在线训练”期间以随机序列出现。“因此，每当训练示例更改为不同的任务时，学习算法必须不断地从学习一个任务切换到另一个任务。这也意味着学习算法必须自动快速地检测任务变化，并利用先前任务的知识来学习新任务。总的来说，自动任务识别福尔斯属于无监督学习的范畴，因为没有向算法提供关于训练示例的任务类别的信息。使用几个人工生成的和三个UCI数据集的算法的性能进行评估。实验结果表明，该算法能够有效地获取和积累任务知识，并通过对已有任务知识的迁移，提高了新任务知识获取的速度。