{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11468147","patent":{"patent_number":"US-11468147","title":"Activation function approximation in deep neural networks using rectified-linear-unit function","assignee":null,"inventors":[],"filing_date":"2020-02-24T00:00:00.000Z","publication_date":"2022-10-11T00:00:00.000Z","cpc_codes":["G06F","G06N","G06N","G06N"],"num_claims":16,"abstract":"A computational apparatus for implementing a neural network model having multiple neurons that evaluate an activation function, the apparatus including a memory and circuitry. The memory is configured to hold values of a difference-function, each value being a respective difference between the activation function and a predefined baseline function. The circuitry is configured to evaluate the neural network model, including, for at least one of the neurons: evaluate the baseline function at the argument, retrieve from the memory one or more values of the difference-function responsively to the argument, and evaluate the activation function at the argument based on the baseline function at the argument and on the one or more values of the difference-function."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Activation function approximation in deep neural networks using rectified-linear-unit function","description":"A computational apparatus for implementing a neural network model having multiple neurons that evaluate an activation function, the apparatus including a memory and circuitry. The memory is configured","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11468147","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-11468147","citation_suggestion":"Patentable. \"Activation function approximation in deep neural networks using rectified-linear-unit function\" (US-11468147). https://patentable.app/patents/US-11468147","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11468147","json":"https://patentable.app/api/llm-context/US-11468147","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T21:54:28.463Z"}