{"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/the-approximation-of-the-dissimilarity","title":"The Approximation of the Dissimilarity Projection","arxiv_id":"1504.00593","date":"2015-04-02","proceeding":null,"authors":["Emanuele Olivetti","Thien Bao Nguyen","Paolo Avesani"],"abstract":"Diffusion magnetic resonance imaging (dMRI) data allow to reconstruct the 3D\npathways of axons within the white matter of the brain as a tractography. The\nanalysis of tractographies has drawn attention from the machine learning and\npattern recognition communities providing novel challenges such as finding an\nappropriate representation space for the data. Many of the current learning\nalgorithms require the input to be from a vectorial space. This requirement\ncontrasts with the intrinsic nature of the tractography because its basic\nelements, called streamlines or tracks, have different lengths and different\nnumber of points and for this reason they cannot be directly represented in a\ncommon vectorial space. In this work we propose the adoption of the\ndissimilarity representation which is an Euclidean embedding technique defined\nby selecting a set of streamlines called prototypes and then mapping any new\nstreamline to the vector of distances from prototypes. We investigate the\ndegree of approximation of this projection under different prototype selection\npolicies and prototype set sizes in order to characterise its use on\ntractography data. Additionally we propose the use of a scalable approximation\nof the most effective prototype selection policy that provides fast and\naccurate dissimilarity approximations of complete tractographies.","url_abs":"http://arxiv.org/abs/1504.00593v1","url_pdf":"http://arxiv.org/pdf/1504.00593v1.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":"the-approximation-of-the-dissimilarity","repo_url":"https://github.com/emanuele/prni2012_dissimilarity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"prototype-selection","task_name":"Prototype Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}