{"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/using-neural-network-formalism-to-solve","title":"Using Neural Network Formalism to Solve Multiple-Instance Problems","arxiv_id":"1609.07257","date":"2016-09-23","proceeding":null,"authors":["Tomas Pevny","Petr Somol"],"abstract":"Many objects in the real world are difficult to describe by a single\nnumerical vector of a fixed length, whereas describing them by a set of vectors\nis more natural. Therefore, Multiple instance learning (MIL) techniques have\nbeen constantly gaining on importance throughout last years. MIL formalism\nrepresents each object (sample) by a set (bag) of feature vectors (instances)\nof fixed length where knowledge about objects (e.g., class label) is available\non bag level but not necessarily on instance level. Many standard tools\nincluding supervised classifiers have been already adapted to MIL setting since\nthe problem got formalized in late nineties. In this work we propose a neural\nnetwork (NN) based formalism that intuitively bridges the gap between MIL\nproblem definition and the vast existing knowledge-base of standard models and\nclassifiers. We show that the proposed NN formalism is effectively optimizable\nby a modified back-propagation algorithm and can reveal unknown patterns inside\nbags. Comparison to eight types of classifiers from the prior art on a set of\n14 publicly available benchmark datasets confirms the advantages and accuracy\nof the proposed solution.","url_abs":"http://arxiv.org/abs/1609.07257v3","url_pdf":"http://arxiv.org/pdf/1609.07257v3.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":"using-neural-network-formalism-to-solve","repo_url":"https://github.com/UnofficialJuliaMirror/Mill.jl-1d0525e4-8992-11e8-313c-e310e1f6ddea","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"using-neural-network-formalism-to-solve","repo_url":"https://github.com/UnofficialJuliaMirrorSnapshots/Mill.jl-1d0525e4-8992-11e8-313c-e310e1f6ddea","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"using-neural-network-formalism-to-solve","repo_url":"https://github.com/pevnak/Mill.jl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.07257","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}