{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11481681","patent":{"patent_number":"US-11481681","title":"Classification robust against multiple perturbation types","assignee":null,"inventors":[],"filing_date":"2020-04-24T00:00:00.000Z","publication_date":"2022-10-25T00:00:00.000Z","cpc_codes":["G06F","G06F","G06N","G06F"],"num_claims":11,"abstract":"A system for training a classification model to be robust against perturbations of multiple perturbation types. A perturbation type defines a set of allowed perturbations. The classification model is trained by, in an outer iteration, selecting a set of training instances of a training dataset; selecting, among perturbations allowed by the multiple perturbation types, one or more perturbations for perturbing the selected training instances to maximize a loss function; and updating the set of parameters of the classification model to decrease the loss for the perturbed instances. A perturbation is determined by, in an inner iteration, determining updated perturbations allowed by respective perturbation types of the multiple perturbation types and selecting an updated perturbation that most increases the loss of the classification model."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Classification robust against multiple perturbation types","description":"A system for training a classification model to be robust against perturbations of multiple perturbation types. A perturbation type defines a set of allowed perturbations. The classification model is ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11481681","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11481681","citation_suggestion":"Patentable. \"Classification robust against multiple perturbation types\" (US-11481681). https://patentable.app/patents/US-11481681","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11481681","json":"https://patentable.app/api/llm-context/US-11481681","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T16:26:29.601Z"}