{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11263518","patent":{"patent_number":"US-11263518","title":"Bi-scaled deep neural networks","assignee":null,"inventors":[],"filing_date":"2019-10-04T00:00:00.000Z","publication_date":"2022-03-01T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N"],"num_claims":11,"abstract":"A method is provided for forming a Deep Neural Network (DNN). The method includes quantizing deep learning data structures of the DNN into at least two modes using at least two scale factors, respectively. Each of the at least two modes corresponds to a respective one of the at least two scale factors. The method further includes identifying which of the at least two scale factors to use for a given one of the data structures based on a data distribution of the given one of the data structures. The quantizing step includes identifying when a tail of the given one of the data structures starts by (i) building a histogram of values in the given one of the data structures using successive bins; (ii) identifying a ratio of density between the successive bins; and (iii) checking whether the ratio of density is greater than a ratio of density threshold."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Bi-scaled deep neural networks","description":"A method is provided for forming a Deep Neural Network (DNN). The method includes quantizing deep learning data structures of the DNN into at least two modes using at least two scale factors, respecti","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11263518","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-11263518","citation_suggestion":"Patentable. \"Bi-scaled deep neural networks\" (US-11263518). https://patentable.app/patents/US-11263518","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11263518","json":"https://patentable.app/api/llm-context/US-11263518","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T20:32:46.569Z"}