{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11263476","patent":{"patent_number":"US-11263476","title":"Unsupervised representation learning with contrastive prototypes","assignee":null,"inventors":[],"filing_date":"2020-05-08T00:00:00.000Z","publication_date":"2022-03-01T00:00:00.000Z","cpc_codes":["G06V","G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06T","G06V","G06V","G06V","G06V","G06T"],"num_claims":20,"abstract":"The system and method are directed to a prototypical contrastive learning (PCL). The PCL explicitly encodes the hierarchical semantic structure of the dataset into the learned embedding space and prevents the network from exploiting low-level cues for solving the unsupervised learning task. The PCL includes prototypes as the latent variables to help find the maximum-likelihood estimation of the network parameters in an expectation-maximization framework. The PCL iteratively performs an E-step for finding prototypes with clustering and M-step for optimizing the network on a contrastive loss."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Unsupervised representation learning with contrastive prototypes","description":"The system and method are directed to a prototypical contrastive learning (PCL). The PCL explicitly encodes the hierarchical semantic structure of the dataset into the learned embedding space and prev","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11263476","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-11263476","citation_suggestion":"Patentable. \"Unsupervised representation learning with contrastive prototypes\" (US-11263476). https://patentable.app/patents/US-11263476","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11263476","json":"https://patentable.app/api/llm-context/US-11263476","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T20:12:12.538Z"}