{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11256987","patent":{"patent_number":"US-11256987","title":"Memory efficient dropout, with reordering of dropout mask elements","assignee":null,"inventors":[],"filing_date":"2021-06-02T00:00:00.000Z","publication_date":"2022-02-22T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N","G06N","G06N","G06N"],"num_claims":23,"abstract":"A method for selectively dropping out feature elements from a tensor is disclosed. The method includes generating a mask that has a plurality of mask elements arranged in a first order. A compressed mask is generated, which includes a plurality of compressed mask elements arranged in a second order that is different from the first order. For example, each mask element of the plurality of mask elements of the mask is compressed to generate a corresponding compressed mask element of the plurality of compressed mask elements of the compressed mask. Individual compressed mask element of the plurality of compressed mask elements is indicative of whether a corresponding feature element of the tensor output by a neural network layer is to be dropped out or retained. Feature elements are selectively dropped from the tensor, based on the compressed mask."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Memory efficient dropout, with reordering of dropout mask elements","description":"A method for selectively dropping out feature elements from a tensor is disclosed. The method includes generating a mask that has a plurality of mask elements arranged in a first order. A compressed m","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11256987","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-11256987","citation_suggestion":"Patentable. \"Memory efficient dropout, with reordering of dropout mask elements\" (US-11256987). https://patentable.app/patents/US-11256987","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11256987","json":"https://patentable.app/api/llm-context/US-11256987","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T19:44:21.977Z"}