Self-Organizing Maps with Convolutional Layers

摘要

Self-organizing maps (SOMs) are well appropriate for visualizing high-dimensional data sets. Training SOMs on raw high-dimensional data with classic metrics often leads to problems arising from the curse-of-dimensionality effect. To achieve more valuable semantic maps of high-dimensional data sets, we assume that higher-level features are necessary. We propose to gather such higher-level features from pre-trained convolutional layers, i.e., filter banks of convolutional neural networks (CNNs). Appropriately pre-trained CNNs are required, e.g., from the same or related domains, or in semi-supervised scenarios. We introduce SOM quality measures and analyze the new approach on two benchmark image data sets considering different convolutional network levels.