{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11983635","patent":{"patent_number":"US-11983635","title":"Methods, systems, apparatuses, and devices for Sifrian-based neural network training","assignee":null,"inventors":[],"filing_date":"2023-10-10T00:00:00.000Z","publication_date":"2024-05-14T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N","G06N","G06N","G06N","G06N"],"num_claims":18,"abstract":"A method for training a neural network model having layers and parameters, comprises providing an input corresponding to each of samples comprised in a batch of a training dataset to an input layer, obtaining outputs from the neural network model, calculating a loss function for each of the samples based on the outputs and corresponding desired values, and determining values for minimizing a mismatch between the outputs and the corresponding desired values across the samples for the parameters based on the loss function. The determining of the values comprises running a forward model through the layers, determining a Sifrian functional for the layers based on the forward model, backpropgation, and gradient definition, determining equations from the Sifrian functional, performing transformation and optionally reduction to get a pivotal Sifr equation and solving the equation to estimate a second-order update for the purpose of the neural network model training."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Methods, systems, apparatuses, and devices for Sifrian-based neural network training","description":"A method for training a neural network model having layers and parameters, comprises providing an input corresponding to each of samples comprised in a batch of a training dataset to an input layer, o","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11983635","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-11983635","citation_suggestion":"Patentable. \"Methods, systems, apparatuses, and devices for Sifrian-based neural network training\" (US-11983635). https://patentable.app/patents/US-11983635","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11983635","json":"https://patentable.app/api/llm-context/US-11983635","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T04:22:22.972Z"}