Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_1bbcd32d9adf88cbba6f84d9576e0c94 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N99-00 |
filingDate |
2018-04-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a9d6aca054bc0354dabb2cb5fe780e14 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_bfe4ab1729825c325b74d34f21d75270 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_063c3f64dae4dd728976452315ec03a0 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6ce51fee74cc20f43edc83160975d98a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f609ff49eddc2e10ff865edc69381e70 |
publicationDate |
2018-10-26-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-108710948-A |
titleOfInvention |
A Migration Learning Method Based on Cluster Equilibrium and Weight Matrix Optimization |
abstract |
The invention discloses a migration learning method based on clustering balance and weight matrix optimization, including defining a source domain sample set and a target domain sample set; reassigning labels of the source domain sample set and target domain sample set samples; Dimensionality reduction of samples in sample set and target domain sample set; feature-based unsupervised cluster analysis of samples in source domain sample set; balance processing for each cluster; learning metric matrix for each cluster; Measure the matrix, generate the weight matrix; optimize the weight matrix; use the weight matrix to predict the label of the sample in the target domain sample set. The present invention divides the source domain sample set into multiple different clusters through an unsupervised clustering analysis method, so that each cluster has similar attributes; at the same time, a weight matrix is generated based on each cluster, and it is optimized, more In line with the actual situation of the target domain sample set, using the weight matrix to predict the label of the target domain sample set has higher accuracy. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110070535-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110555060-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110009038-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109934281-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110555060-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111209935-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-109934281-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111161239-A |
priorityDate |
2018-04-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |