{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11526755","patent":{"patent_number":"US-11526755","title":"Training more secure neural networks by using local linearity regularization","assignee":null,"inventors":[],"filing_date":"2020-05-22T00:00:00.000Z","publication_date":"2022-12-13T00:00:00.000Z","cpc_codes":["G06N","G06F","G06F","G06V","G06V","G06V","G06N"],"num_claims":20,"abstract":"Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes processing each training input using the neural network and in accordance with the current values of the network parameters to generate a network output for the training input; computing a respective loss for each of the training inputs by evaluating a loss function; identifying, from a plurality of possible perturbations, a maximally non-linear perturbation; and determining an update to the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to decrease the respective losses for the training inputs and to decrease the non-linearity of the loss function for the identified maximally non-linear perturbation."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Training more secure neural networks by using local linearity regularization","description":"Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes processing each training input using the neur","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11526755","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-11526755","citation_suggestion":"Patentable. \"Training more secure neural networks by using local linearity regularization\" (US-11526755). https://patentable.app/patents/US-11526755","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11526755","json":"https://patentable.app/api/llm-context/US-11526755","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T20:36:54.303Z"}