{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11526761","patent":{"patent_number":"US-11526761","title":"Neural network training with decreased memory consumption and processor utilization","assignee":null,"inventors":[],"filing_date":"2019-08-24T00:00:00.000Z","publication_date":"2022-12-13T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N"],"num_claims":20,"abstract":"Bounding box quantization can reduce the quantity of bits utilized to express numerical values prior to the multiplication of matrices comprised of such numerical values, thereby reducing both memory consumption and processor utilization. Stochastic rounding can provide sufficient precision to enable the storage of weight values in reduced-precision formats without having to separately store weight values in a full-precision format. Alternatively, other rounding mechanisms, such as round to nearest, can be utilized to exchange weight values in reduced-precision formats, while also storing weight values in full-precision formats for subsequent updating. To facilitate conversion, reduced-precision formats such as brain floating-point format can be utilized."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Neural network training with decreased memory consumption and processor utilization","description":"Bounding box quantization can reduce the quantity of bits utilized to express numerical values prior to the multiplication of matrices comprised of such numerical values, thereby reducing both memory ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11526761","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-11526761","citation_suggestion":"Patentable. \"Neural network training with decreased memory consumption and processor utilization\" (US-11526761). https://patentable.app/patents/US-11526761","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11526761","json":"https://patentable.app/api/llm-context/US-11526761","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T14:46:58.031Z"}