http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20200053170-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_b511ad5f7957ddf582d2a149a3efd8df http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_0b7a72e18a05bccf4393c6a46058bde9 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ed60c85c16ddd15ed376180d30a98072 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-063 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-44505 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N99-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-063 |
filingDate | 2018-11-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_32793e47c7ff7e4fc8f4b078899805cd http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e754215aa775a560ce2812dac6f315e6 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_06b4895f7cd8418cc52deccfec0cb2a5 |
publicationDate | 2020-05-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | KR-20200053170-A |
titleOfInvention | Method for setting artificial intelligence execution model and system for acceleration a.i execution |
abstract | It provides an AI execution acceleration system and an AI execution model setting method. The AI execution acceleration system according to the embodiment analyzes a learning model including a weight file and an AI model generated as a result of AI learning, and executes a weight to calculate data weights of the AI learning model for accelerating AI execution. Extraction module; Artificial intelligence that loads the learning model from the AI learning server that calculates the learning model, converts the loaded learning model into a custom layer available in the AI execution acceleration system, and optimizes the custom layer to calculate the execution model Intelligent acceleration executable file setting module; And an artificial intelligence execution acceleration module that receives an execution model and configures an execution environment corresponding to the execution model to accelerate artificial intelligence execution speed. It includes. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20220046038-A |
priorityDate | 2018-11-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419557109 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID23954 |
Total number of triples: 25.