{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11531884","patent":{"patent_number":"US-11531884","title":"Separate quantization method of forming combination of 4-bit and 8-bit data of neural network","assignee":null,"inventors":[],"filing_date":"2019-09-27T00:00:00.000Z","publication_date":"2022-12-20T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N","G06N","G06N","G06N"],"num_claims":11,"abstract":"A separate quantization method of forming a combination of 4-bit and 8-bit data of a neural network is disclosed. When a training data set and a validation data set exist, a calibration manner is used to determine a threshold for activations of each of a plurality of layers of a neural network model, so as to determine how many of the activations to perform 8-bit quantization. In a process of weight quantization, the weights of each layer are allocated to 4-bit weights and 8-bit weights according to a predetermined ratio, so as to make the neural network model have a reduced size and a combination of 4-bit and 8-bit weights."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Separate quantization method of forming combination of 4-bit and 8-bit data of neural network","description":"A separate quantization method of forming a combination of 4-bit and 8-bit data of a neural network is disclosed. When a training data set and a validation data set exist, a calibration manner is used","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11531884","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-11531884","citation_suggestion":"Patentable. \"Separate quantization method of forming combination of 4-bit and 8-bit data of neural network\" (US-11531884). https://patentable.app/patents/US-11531884","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11531884","json":"https://patentable.app/api/llm-context/US-11531884","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T03:22:32.162Z"}