论文标题
关于机器学习应用程序中时空信息的保存
On the Preservation of Spatio-temporal Information in Machine Learning Applications
论文作者
论文摘要
在常规的机器学习应用程序中，假定每个数据属性与他人是正交的。也就是说，每对维度彼此之间都是正交的，因此尺寸之间的关系没有区别。但是，在现实世界中自然源自时空配置的现实信号肯定不是这种情况。结果，常规矢量化过程破坏了有关数据订单/地点的所有时空信息，无论是$ 1 $ d，$ 2 $ d，$ 3 $ d还是$ 4 $ d。在本文中，首先通过传统的$ k $ - 表示图像来调查正交性的问题，其中图像要作为向量处理。作为解决方案，在稀疏表示的帮助下，在一个新颖的框架中提出了Shift-Invariant $ k $ -Means。然后将转移不变的$ k $ - 均值（卷积词典学习）的概括用作无监督的分类特征提取方法。实验表明，与卷积词典学习相比，Gabor特征提取作为浅卷积神经网络的模拟提供了更好的性能。还讨论了许多卷积逻辑的替代方法，以进行时空信息保存，包括时空超复杂的编码方案。
In conventional machine learning applications, each data attribute is assumed to be orthogonal to others. Namely, every pair of dimension is orthogonal to each other and thus there is no distinction of in-between relations of dimensions. However, this is certainly not the case in real world signals which naturally originate from a spatio-temporal configuration. As a result, the conventional vectorization process disrupts all of the spatio-temporal information about the order/place of data whether it be $1$D, $2$D, $3$D, or $4$D. In this paper, the problem of orthogonality is first investigated through conventional $k$-means of images, where images are to be processed as vectors. As a solution, shift-invariant $k$-means is proposed in a novel framework with the help of sparse representations. A generalization of shift-invariant $k$-means, convolutional dictionary learning, is then utilized as an unsupervised feature extraction method for classification. Experiments suggest that Gabor feature extraction as a simulation of shallow convolutional neural networks provides a little better performance compared to convolutional dictionary learning. Many alternatives of convolutional-logic are also discussed for spatio-temporal information preservation, including a spatio-temporal hypercomplex encoding scheme.
