{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11521014","patent":{"patent_number":"US-11521014","title":"L2-nonexpansive neural networks","assignee":null,"inventors":[],"filing_date":"2019-02-04T00:00:00.000Z","publication_date":"2022-12-06T00:00:00.000Z","cpc_codes":["G06N","G06F","G06F","G06F","G06N","G06N","G06N","G06V","G06V","G06N","G06N"],"num_claims":20,"abstract":"A training method, system, and computer program product include computing a matrix norm over a product of a weight matrix and a transpose of the weight matrix and using the matrix norm to constrain the L2 non-expansive neural network."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"L2-nonexpansive neural networks","description":"A training method, system, and computer program product include computing a matrix norm over a product of a weight matrix and a transpose of the weight matrix and using the matrix norm to constrain th","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11521014","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-11521014","citation_suggestion":"Patentable. \"L2-nonexpansive neural networks\" (US-11521014). https://patentable.app/patents/US-11521014","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11521014","json":"https://patentable.app/api/llm-context/US-11521014","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T23:31:40.342Z"}