2019/08/01 by Kenji Fukushima, Fukushima, Kenji, Shotaro Shiba Funai +3 · 1 citation
Computer Science · Earth and Planetary Sciences · Engineering · Physics and Astronomy · #FOS: Computer and information sciences #FOS: Physical sciences #Geological Modeling and Analysis #High Energy Physics - Theory (hep-th) #Machine Learning (cs.LG) #Power Systems and Technologies #cs.LG #hep-th
paper · pdf · doi:10.48550/arxiv.1908.00281
14 pages, 7 figures
arxiv created 2019/08/01 · openalex publication_date 2019/08/01 · arxiv updated 2019/08/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Images of line drawings are generally composed of primitive elements. One of the most fundamental elements to characterize images is the topology; line segments belong to a category different from closed circles, and closed circles with different winding degrees are nonequivalent. We investigate images with nontrivial winding using the unsupervised machine learning. We build an autoencoder model with a combination of convolutional and fully connected neural networks. We confirm that compressed data filtered from the trained model retain more than 90% of correct information on the topology, evidencing that image clustering from the unsupervised learning features the topology.