{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11521062","patent":{"patent_number":"US-11521062","title":"Neural network training using a data flow graph and dynamic memory management","assignee":null,"inventors":[],"filing_date":"2019-12-05T00:00:00.000Z","publication_date":"2022-12-06T00:00:00.000Z","cpc_codes":["G06N","G06F","G06F","G06F","G06N","G06N","G06N","G06N","G06N"],"num_claims":23,"abstract":"Processing a neural network data flow graph having a set of nodes and a set of edges. An insertion point is determined for a memory reduction or memory restoration operation. The determination is based on computing tensor timing slacks (TTS) for a set of input tensors; compiling a candidate list (SI) of input tensors, from the set of input tensors, using input tensors having corresponding TTS values larger than a threshold value (thTTS); filtering the SI to retain input tensors whose size meets a threshold value (thS); and determining an insertion point for the operation using the SI based on the filtering. A new data flow graph is generated or an existing one is modified using this process."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Neural network training using a data flow graph and dynamic memory management","description":"Processing a neural network data flow graph having a set of nodes and a set of edges. An insertion point is determined for a memory reduction or memory restoration operation. The determination is base","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11521062","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-11521062","citation_suggestion":"Patentable. \"Neural network training using a data flow graph and dynamic memory management\" (US-11521062). https://patentable.app/patents/US-11521062","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11521062","json":"https://patentable.app/api/llm-context/US-11521062","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T07:58:48.138Z"}