{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-10546236","patent":{"patent_number":"US-10546236","title":"Training multiple neural networks with different accuracy","assignee":null,"inventors":[],"filing_date":"2016-09-09T00:00:00.000Z","publication_date":"2020-01-28T00:00:00.000Z","cpc_codes":["G06F","G06N","G06F","G06F","G06N","G06N","G10L"],"num_claims":21,"abstract":"Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a deep neural network. One of the methods includes generating a plurality of feature vectors that each model a different portion of an audio waveform, generating a first posterior probability vector for a first feature vector using a first neural network, determining whether one of the scores in the first posterior probability vector satisfies a first threshold value, generating a second posterior probability vector for each subsequent feature vector using a second neural network, wherein the second neural network is trained to identify the same key words and key phrases and includes more inner layer nodes than the first neural network, and determining whether one of the scores in the second posterior probability vector satisfies a second threshold value."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Training multiple neural networks with different accuracy","description":"Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a deep neural network. One of the methods includes generating a plurality of feature vector","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-10546236","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-10546236","citation_suggestion":"Patentable. \"Training multiple neural networks with different accuracy\" (US-10546236). https://patentable.app/patents/US-10546236","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-10546236","json":"https://patentable.app/api/llm-context/US-10546236","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T17:38:02.654Z"}