可扩展迁移学习中跨媒体复杂问题自动映射研究

项目名称： 可扩展迁移学习中跨媒体复杂问题自动映射研究

项目编号： No.U1204610

项目类型： 联合基金项目

立项/批准年度： 2013

项目学科： 计算机科学学科

项目作者： 朱真峰

作者单位： 郑州大学

项目金额： 31万元

中文摘要： 迁移学习打破了传统机器学习方法中训练集(相关任务)和测试集(目标任务)服从同分布的假设，能够处理分布发生变化的数据，有助于设计更加智能化的机器学习方法。本项目针对迁移学习中存在的关键问题：复杂任务间可扩展模型的建立，映射空间维数的确定，自动映射的实现等问题；以层次贝叶斯方法、深度学习方法和增量式方法建立不同任务间的抽象知识表示模型；采用信息熵、最小描述长度准则及近邻传播方法来确定特征维数；拟用多变量IB方法和矩阵论方法处理自动映射问题；项目拟采用不同的迁移学习模型，进行跨媒体模式识别和自动相互注解的研究，力图发现迁移学习所适应的问题特征及数学规律。该项目的研究，一方面有利于设计更加拟人化的机器学习算法，为人工智能的发展提供新的思路和途径，另一方面将迁移学习方法用于海量数据分析，跨媒体模式识别，从而为建立动态快速的决策系统提供坚实的基础。

中文关键词： 迁移学习；增量式学习；矩阵方法；大规模数据；高维数据

英文摘要： Traditional machine learning methods assume the training sets and test sets share the same distributions, however, in many applications, data distributions are dynamically changeable. In contrast, transfer learning considers that the related tasks and target tasks have different distributions. Then, methods of this kind can deal with dynamic data, which is useful to design better intelligent machine learning methods than traditional ones. In the research of transfer learning, there still exists some crucial problems: 1) how to construct the scalable models among complex tasks, 2) how to choose the number of dimensionality in feature spaces, and 3) how to achieve automatical mapping among complex tasks. To solve the problems described above, we employ and reconstruct the following methods: Hierarchical Bayesian, deep leaning and incremental learning methods are used to build the representation models of abstract knowledge between different tasks; Informtion Entropy, Minimum Description Length (MDL) and Affinity Propagation (AP) are used to decide the number of feature dimensions; Multivariate information bottleneck (MIB), and matrix theorem based methods are used to obtain automatic mapping. In practical applications, this project uses different transfer learning models to study the pattern recognition and autom

英文关键词： transfer learning；incremental learning；matrix based mathods；large scale data；high dimensional data