{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11507844","patent":{"patent_number":"US-11507844","title":"Asynchronous evaluation strategy for evolution of deep neural networks","assignee":null,"inventors":[],"filing_date":"2018-03-07T00:00:00.000Z","publication_date":"2022-11-22T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N","G06T"],"num_claims":31,"abstract":"The technology disclosed proposes a novel asynchronous evaluation strategy (AES) that increases throughput of evolutionary algorithms by continuously maintaining a queue of K individuals ready to be sent to the worker nodes for evaluation and evolving the next generation once a fraction Mi of the K individuals have been evaluated by the worker nodes, where Mi<<K. A suitable value for Mi is determined experimentally, balancing diversity and efficiency. The technology disclosed is extended to coevolution of deep neural network supermodules and blueprints in the form of AES for cooperative evolution of deep neural networks (CoDeepNEAT-AES). Applied to image captioning domain, a threefold speedup is observed on 200 graphics processing unit (GPU) worker nodes, demonstrating that the disclosed AES and CoDeepNEAT-AES are promising techniques for evolving complex systems with long and variable evaluation times."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Asynchronous evaluation strategy for evolution of deep neural networks","description":"The technology disclosed proposes a novel asynchronous evaluation strategy (AES) that increases throughput of evolutionary algorithms by continuously maintaining a queue of K individuals ready to be s","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11507844","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-11507844","citation_suggestion":"Patentable. \"Asynchronous evaluation strategy for evolution of deep neural networks\" (US-11507844). https://patentable.app/patents/US-11507844","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11507844","json":"https://patentable.app/api/llm-context/US-11507844","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T16:25:46.162Z"}