http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108875906-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
| filingDate | 2018-04-20-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2019-06-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2019-06-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-108875906-B |
| titleOfInvention | A multi-scale step-by-step accumulation convolutional neural network learning method |
| abstract | The invention relates to a multi-scale step-by-step accumulation convolutional neural network learning method, which can be widely used in the fields of machine vision and artificial intelligence, such as target detection, target classification, target recognition and the like. First, the present invention uses the mean pooling operation to construct a multi-scale image pyramid for the input image; then, the images of different scales are gradually fed into the convolutional neural network, so that the convolutional neural network can be used in multiple Learning on images of different scales and gradually accumulating features improves the feature learning ability of the convolutional neural network. |
| priorityDate | 2018-04-20-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 37.