| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_a68790a12228f5b99e176e8aacff640a |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30201 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-001
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-006
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0012
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-02
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-50
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N5-046
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-00 |
| filingDate |
2020-10-12^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7ef855073b9d9f4011c54c16a3271cd0
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_40bf7124ff63d85d4d205a00ab6070c0
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c953298f35a98aee5ce56ed38cef59f9
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_15772e07a3888542e5a566b93ec11a69
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c0351b4016009ec848506e9a8453cfa6 |
| publicationDate |
2021-09-14^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-113392968-A |
| titleOfInvention |
Iterative Small-Sample Refinement Microtraining for Neural Networks |
| abstract |
The invention discloses iterative small sample refinement micro-training for neural networks. The disclosed microtraining technique improves the accuracy of trained neural networks by performing iterative refinement at a low learning rate using a relatively short series of microtraining steps. The neural network training framework receives the trained neural network and the second training dataset and hyperparameter set. The neural network training framework facilitates incremental accuracy improvements by using a lower learning rate to adjust one or more weights of the trained neural network, without essentially changing the computational structure of the trained neural network, resulting in Microtrained Neural Networks. Changes in accuracy and/or quality of a microtrained neural network can be assessed. Additional microtraining sessions can be performed on the microtrained neural network to further improve accuracy or quality. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114331806-A |
| priorityDate |
2020-03-13^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |