| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_bc905cbef116a1ec61d12125af9427f3 |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30148
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30141
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N2021-8883
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N2021-95646
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N2201-1296
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30152
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-02
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-001
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0002
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N21-956 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-02
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-00 |
| filingDate |
2019-12-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d2e8d389abc0ada42de4691fe762e205
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_32f6c6ce5ecac250eb39af23ff1cba22
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5baa791c703fa059a2d292295805a113
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0319a8624f4ddff49a015f6e84fca088 |
| publicationDate |
2021-06-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-112907502-A |
| titleOfInvention |
Training device and training method of neural network model |
| abstract |
The present disclosure provides a training device and a training method for a neural network model, wherein the training method includes: obtaining a data set; completing multiple artificial intelligence model trainings according to the data set to generate multiple models corresponding to the multiple artificial intelligence model trainings respectively ; selecting a first model set from a plurality of models according to a first constraint condition; and selecting a neural network model from the first model set according to a second constraint condition. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113284141-A |
| priorityDate |
2019-12-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |