{"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/neural-state-classification-for-hybrid","title":"Neural State Classification for Hybrid Systems","arxiv_id":"1807.09901","date":"2018-07-26","proceeding":null,"authors":["Dung Phan","Nicola Paoletti","Timothy Zhang","Radu Grosu","Scott A. Smolka","Scott D. Stoller"],"abstract":"We introduce the State Classification Problem (SCP) for hybrid systems, and\npresent Neural State Classification (NSC) as an efficient solution technique.\nSCP generalizes the model checking problem as it entails classifying each state\n$s$ of a hybrid automaton as either positive or negative, depending on whether\nor not $s$ satisfies a given time-bounded reachability specification. This is\nan interesting problem in its own right, which NSC solves using\nmachine-learning techniques, Deep Neural Networks in particular. State\nclassifiers produced by NSC tend to be very efficient (run in constant time and\nspace), but may be subject to classification errors. To quantify and mitigate\nsuch errors, our approach comprises: i) techniques for certifying, with\nstatistical guarantees, that an NSC classifier meets given accuracy levels; ii)\ntuning techniques, including a novel technique based on adversarial sampling,\nthat can virtually eliminate false negatives (positive states classified as\nnegative), thereby making the classifier more conservative. We have applied NSC\nto six nonlinear hybrid system benchmarks, achieving an accuracy of 99.25% to\n99.98%, and a false-negative rate of 0.0033 to 0, which we further reduced to\n0.0015 to 0 after tuning the classifier. We believe that this level of accuracy\nis acceptable in many practical applications, and that these results\ndemonstrate the promise of the NSC approach.","url_abs":"http://arxiv.org/abs/1807.09901v1","url_pdf":"http://arxiv.org/pdf/1807.09901v1.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":"neural-state-classification-for-hybrid","repo_url":"https://github.com/moduIo/Neural-State-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"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}