{"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/an-iterative-closest-points-approach-to","title":"An Iterative Closest Points Approach to Neural Generative Models","arxiv_id":"1711.06562","date":"2017-11-16","proceeding":null,"authors":["Joose Rajamäki","Perttu Hämäläinen"],"abstract":"We present a simple way to learn a transformation that maps samples of one\ndistribution to the samples of another distribution. Our algorithm comprises an\niteration of 1) drawing samples from some simple distribution and transforming\nthem using a neural network, 2) determining pairwise correspondences between\nthe transformed samples and training data (or a minibatch), and 3) optimizing\nthe weights of the neural network being trained to minimize the distances\nbetween the corresponding vectors. This can be considered as a variant of the\nIterative Closest Points (ICP) algorithm, common in geometric computer vision,\nalthough ICP typically operates on sensor point clouds and linear transforms\ninstead of random sample sets and neural nonlinear transforms. We demonstrate\nthe algorithm on simple synthetic data and MNIST data. We furthermore\ndemonstrate that the algorithm is capable of handling distributions with both\ncontinuous and discrete variables.","url_abs":"http://arxiv.org/abs/1711.06562v4","url_pdf":"http://arxiv.org/pdf/1711.06562v4.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":"an-iterative-closest-points-approach-to","repo_url":"https://github.com/JooseRajamaeki/ICP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}