{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11941507","patent":{"patent_number":"US-11941507","title":"Data flow method and apparatus for neural network computation by determining input variables and output variables of nodes of a computational graph of a neural network","assignee":null,"inventors":[],"filing_date":"2022-09-27T00:00:00.000Z","publication_date":"2024-03-26T00:00:00.000Z","cpc_codes":["G06N","G06N","G06F"],"num_claims":3,"abstract":"Disclosed are a data flow method and apparatus for neural network computation. The data flow method for neural network computation includes initializing the lifecycle of a variable in a computational graph; and defining a propagation rule for a variable in use to flow through a node. A definition of the variable is produced at a precursor node of the node, such that an input set of valid variables flowing through the node contains the variable. The method may be used on neural network computation in a deep learning training system."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Data flow method and apparatus for neural network computation by determining input variables and output variables of nodes of a computational graph of a neural network","description":"Disclosed are a data flow method and apparatus for neural network computation. The data flow method for neural network computation includes initializing the lifecycle of a variable in a computational ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11941507","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-11941507","citation_suggestion":"Patentable. \"Data flow method and apparatus for neural network computation by determining input variables and output variables of nodes of a computational graph of a neural network\" (US-11941507). https://patentable.app/patents/US-11941507","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11941507","json":"https://patentable.app/api/llm-context/US-11941507","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T17:58:32.699Z"}