{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11977974","patent":{"patent_number":"US-11977974","title":"Compression of fully connected / recurrent layers of deep network(s) through enforcing spatial locality to weight matrices and effecting frequency compression","assignee":null,"inventors":[],"filing_date":"2017-11-30T00:00:00.000Z","publication_date":"2024-05-07T00:00:00.000Z","cpc_codes":["G06N","G06N","G06F","G06N","G06N","G06N","G06N","G06N"],"num_claims":12,"abstract":"A system, having a memory that stores computer executable components, and a processor that executes the computer executable components, reduces data size in connection with training a neural network by exploiting spatial locality to weight matrices and effecting frequency transformation and compression. A receiving component receives neural network data in the form of a compressed frequency-domain weight matrix. A segmentation component segments the initial weight matrix into original sub-components, wherein respective original sub-components have spatial weights. A sampling component applies a generalized weight distribution to the respective original sub-components to generate respective normalized sub-components. A transform component applies a transform to the respective normalized sub-components. A cropping component crops high-frequency weights of the respective transformed normalized sub-components to yield a set of low-frequency normalized sub-components to generate a compressed representation of the original sub-components."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Compression of fully connected / recurrent layers of deep network(s) through enforcing spatial locality to weight matrices and effecting frequency compression","description":"A system, having a memory that stores computer executable components, and a processor that executes the computer executable components, reduces data size in connection with training a neural network b","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11977974","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-11977974","citation_suggestion":"Patentable. \"Compression of fully connected / recurrent layers of deep network(s) through enforcing spatial locality to weight matrices and effecting frequency compression\" (US-11977974). https://patentable.app/patents/US-11977974","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11977974","json":"https://patentable.app/api/llm-context/US-11977974","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T12:37:18.658Z"}