{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/180302972","title":"SLADS-Net: Supervised Learning Approach for Dynamic Sampling using Deep Neural Networks","arxiv_id":"1803.02972","date":"2018-03-08","proceeding":null,"authors":["Yan Zhang","G. M. Dilshan Godaliyadda","Nicola Ferrier","Emine B. Gulsoy","Charles A. Bouman","Charudatta Phatak"],"abstract":"In scanning microscopy based imaging techniques, there is a need to develop\nnovel data acquisition schemes that can reduce the time for data acquisition\nand minimize sample exposure to the probing radiation. Sparse sampling schemes\nare ideally suited for such applications where the images can be reconstructed\nfrom a sparse set of measurements. In particular, dynamic sparse sampling based\non supervised learning has shown promising results for practical applications.\nHowever, a particular drawback of such methods is that it requires training\nimage sets with similar information content which may not always be available.\nIn this paper, we introduce a Supervised Learning Approach for Dynamic Sampling\n(SLADS) algorithm that uses a deep neural network based training approach. We\ncall this algorithm SLADS- Net. We have performed simulated experiments for\ndynamic sampling using SLADS-Net in which the training images either have\nsimilar information content or completely different information content, when\ncompared to the testing images. We compare the performance across various\nmethods for training such as least- squares, support vector regression and deep\nneural networks. From these results we observe that deep neural network based\ntraining results in superior performance when the training and testing images\nare not similar. We also discuss the development of a pre-trained SLADS-Net\nthat uses generic images for training. Here, the neural network parameters are\npre-trained so that users can directly apply SLADS-Net for imaging experiments.","url_abs":"http://arxiv.org/abs/1803.02972v1","url_pdf":"http://arxiv.org/pdf/1803.02972v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"180302972","repo_url":"https://github.com/cphatak/SLADS-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}