{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11501165","patent":{"patent_number":"US-11501165","title":"Contrastive neural network training in an active learning environment","assignee":null,"inventors":[],"filing_date":"2020-03-04T00:00:00.000Z","publication_date":"2022-11-15T00:00:00.000Z","cpc_codes":["G06N","G06F","G06F","G06F","G06F","G06F","G06F","G06N","G06N"],"num_claims":20,"abstract":"Embodiments relate to a system, program product, and method for training a contrastive neural network (CNN) in an active learning environment. A neural network is pre-trained with labeled data of a historical (first) dataset. The CNN is trained for a new (second) dataset by applying the new dataset and contrasting the new dataset against the historical dataset to extract novel patterns. Weights of a knowledge operator from the pre-trained neural network are borrowed. Features novel to the new dataset are learned, including updating weights of the knowledge operator. The borrowed knowledge operator weights are combined with the updated knowledge operator weights. The CNN is leveraged to predict one or more labels for the new dataset as output data."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Contrastive neural network training in an active learning environment","description":"Embodiments relate to a system, program product, and method for training a contrastive neural network (CNN) in an active learning environment. A neural network is pre-trained with labeled data of a hi","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11501165","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-11501165","citation_suggestion":"Patentable. \"Contrastive neural network training in an active learning environment\" (US-11501165). https://patentable.app/patents/US-11501165","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11501165","json":"https://patentable.app/api/llm-context/US-11501165","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T15:36:48.629Z"}