{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11983634","patent":{"patent_number":"US-11983634","title":"Multi-task neural network systems with task-specific policies and a shared policy","assignee":null,"inventors":[],"filing_date":"2021-09-27T00:00:00.000Z","publication_date":"2024-05-14T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N","G06N","G06N","G06N"],"num_claims":20,"abstract":"A method is proposed for training a multitask computer system, such as a multitask neural network system. The system comprises a set of trainable workers and a shared module. The trainable workers and shared module are trained on a plurality of different tasks, such that each worker learns to perform a corresponding one of the tasks according to a respective task policy, and said shared policy network learns a multitask policy which represents common behavior for the tasks. The coordinated training is performed by optimizing an objective function comprising, for each task: a reward term indicative of an expected reward earned by a worker in performing the corresponding task according to the task policy; and at least one entropy term which regularizes the distribution of the task policy towards the distribution of the multitask policy."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Multi-task neural network systems with task-specific policies and a shared policy","description":"A method is proposed for training a multitask computer system, such as a multitask neural network system. The system comprises a set of trainable workers and a shared module. The trainable workers and","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11983634","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-11983634","citation_suggestion":"Patentable. \"Multi-task neural network systems with task-specific policies and a shared policy\" (US-11983634). https://patentable.app/patents/US-11983634","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11983634","json":"https://patentable.app/api/llm-context/US-11983634","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T14:42:34.603Z"}