Statistical mechanics of dictionary learning
Statistical mechanics of dictionary learning
复制标题
DOI：
10.1209/0295-5075/103/28008
复制
发表时间：
2012-03
期刊：
影响因子：
--
通讯作者：
A. Sakata;Y. Kabashima
中科院分区：
文献类型：
--
作者：
A. Sakata;Y. Kabashima
寻找一个基矩阵（字典），用它来稀疏地表示客观信号，在各种科学和技术领域具有重要的相关性。我们考虑一个从一组训练信号中学习字典的问题。我们采用无序系统的统计力学技术来评估字典学习成功所需的训练集的大小。结果表明，所需的大小比先前估计的要小得多，这在理论上支持和/或鼓励在实际情况下使用字典学习。
Finding a basis matrix (dictionary) by which objective signals are represented sparsely is of major relevance in various scientific and technological fields. We consider a problem to learn a dictionary from a set of training signals. We employ techniques of statistical mechanics of disordered systems to evaluate the size of the training set necessary to typically succeed in the dictionary learning. The results indicate that the necessary size is much smaller than previously estimated, which theoretically supports and/or encourages the use of dictionary learning in practical situations.