{"id":17163324,"url":"https://github.com/iglesias/netpred","last_synced_at":"2026-01-05T12:43:49.636Z","repository":{"id":7584706,"uuid":"8940391","full_name":"iglesias/netpred","owner":"iglesias","description":"Structured learning with SVMs in C++ and Python","archived":false,"fork":false,"pushed_at":"2023-04-20T07:55:50.000Z","size":3371,"stargazers_count":3,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-29T21:54:42.398Z","etag":null,"topics":["hidden-markov-model","machine-learning","network-science","probabilistic-graphical-models","support-vector-machines"],"latest_commit_sha":null,"homepage":"","language":"OpenEdge ABL","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iglesias.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2013-03-21T22:51:39.000Z","updated_at":"2023-12-07T19:45:52.000Z","dependencies_parsed_at":"2024-12-05T18:01:17.025Z","dependency_job_id":null,"html_url":"https://github.com/iglesias/netpred","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iglesias%2Fnetpred","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iglesias%2Fnetpred/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iglesias%2Fnetpred/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iglesias%2Fnetpred/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iglesias","download_url":"https://codeload.github.com/iglesias/netpred/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245315230,"owners_count":20595213,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["hidden-markov-model","machine-learning","network-science","probabilistic-graphical-models","support-vector-machines"],"created_at":"2024-10-14T22:48:40.737Z","updated_at":"2026-01-05T12:43:49.582Z","avatar_url":"https://github.com/iglesias.png","language":"OpenEdge ABL","funding_links":[],"categories":[],"sub_categories":[],"readme":"netpred\n=======\n\nStructured SVMs applied to label sequence learning (the so-called HM-SVM) and\ngraph learning (or grid CRFs in particular). I am using\nthis code to carry out some experiments during my final degree project. A lot\nof inspiration has been drawn from [pystruct](http://github.com/amueller/pystruct)\nby Andreas Mueller for the graph learning part. The HM-SVM implementation in\nShogun I am using here is based on the Matlab code by Gunnar Raetsch and Georg\nZeller [available at mloss](http://mloss.org/software/tags/hmsvm/). The code\nmakes use of [Shogun](http://shogun-toolbox.org)'s structured learning framework\n([+ info](https://iglesiashogun.wordpress.com/2012/05/22/first-weekly-report-gsoc-2012/)).\n\nRequirements\n============\n\nYou definetely need Shogun and Swig. Also, you need to compile Shogun with\ndirectors enabled and at least target Python's modular interface. In addition,\nwith the current state you need to compile Shogun with Mosek support. This\ndependency should be easy to remove though by using any of the bundle methods\nfor SSVMs present in Shogun.\n\nThere are a couple of subgradient methods implemented in the graph directory.\nUsing this, you do not need Mosek. I have only tested them in the\ngraph learning task, but in principle they should work fine for label\nsequence learning as well.\n\nApart from Shogun dependencies, you need cvxopt for the linear programming\nrelaxation used to solve the argmax in graph learning.\n\nReport and presentation\n=======================\n\nFeel free to reach out if you would like to read my final degree project (PFC in Spanish) report.\n[Video](https://www.youtube.com/watch?v=Ti_Wivo9OWY) of a presentation during the Shogun Workshop 2013.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Figlesias%2Fnetpred","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Figlesias%2Fnetpred","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Figlesias%2Fnetpred/lists"}