{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11245903","patent":{"patent_number":"US-11245903","title":"Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression","assignee":null,"inventors":[],"filing_date":"2020-11-16T00:00:00.000Z","publication_date":"2022-02-08T00:00:00.000Z","cpc_codes":["H04N","G06N","G06N","H04N","H04N","H04N","H04N","H04N","H04N","H04N","H04N","H04N"],"num_claims":18,"abstract":"A method of quantization, adaptive block partitioning and codebook coding for neural network model compression, is performed by at least one processor and includes determining a saturated maximum value of a multi-dimensional tensor in a layer of a neural network, and a bit depth corresponding to the saturated maximum value, and clipping weight coefficients in the multi-dimensional tensor to be within a range of the saturated maximum value. The method further includes quantizing the clipped weight coefficients, based on the bit depth, and transmitting, to a decoder, a layer header including the bit depth."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression","description":"A method of quantization, adaptive block partitioning and codebook coding for neural network model compression, is performed by at least one processor and includes determining a saturated maximum valu","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11245903","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-11245903","citation_suggestion":"Patentable. \"Method and apparatus for quantization, adaptive block partitioning and codebook coding for neural network model compression\" (US-11245903). https://patentable.app/patents/US-11245903","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11245903","json":"https://patentable.app/api/llm-context/US-11245903","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T21:54:58.560Z"}