Visualization of Learning Process in Feature Space

Abstract

In machine learning, the structure of feature space is an important factor that determines the performance of a model. Therefore, we can deepen our understanding of learning algorithms if we can visualize changes in the structure of feature space during the learning process. However, visualizing such changes is difficult because it requires dimensionality reduction while maintaining consistency with the data structure in high-dimensional space and in the temporal direction. In this study, we visualized feature changes during the learning process by capturing them as changes in the positional relationship between target features and time-invariant reference coordinates with a log-bilinear model.