http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-H04277859-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_73f3ee783fb85a0922c61edf071c6db7 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_0950e9df7f0e1b73efee1bda859951ad |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F15-18 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N99-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06G7-60 |
| filingDate | 1991-03-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_22ddd7e74f4204ccc654252626fce6b3 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a843030d6d68dc2cfa5ebaf6b284a8e6 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b48eece4f20701922c28334504272db3 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ec929ffb064f7a9fbd765a2a222da499 |
| publicationDate | 1992-10-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | JP-H04277859-A |
| titleOfInvention | Method and device for estimation by neural network |
| abstract | PURPOSE: To facilitate the learning of a new conception and to simply and easily execute estimation when inputting a new/old mixed conception by overlapping a new neural network above the hierarchy of an old neural network. n CONSTITUTION: A new neural network 50 is provided above the hierarchy of an old neural network 40, which already learns the old conception, and a change component from the old conception is newly learnt from the conception mixing the old and new conceptions by the new neural network 50. Then, the output of the old neural network 40 and the output of the new neural network 50 are added, and the new/old mixing conception is estimated. For example, in a neural network 60 constituted by using a learnt new neural network (GNET) 50, the first hierarchy is defined as the old neural network 40 to input only the uranium enrichment signal, the second hierarchy is defined as the new neural network 50 to input both the uranium enrichment signal and a GD density signal. Therefore, by adding the both output signals at an adding means 67, a prescribed physical amount (LPF) 77 expressing core performance considering respective effects can be obtained. n COPYRIGHT: (C)1992,JPO&Japio |
| priorityDate | 1991-03-05-04:00^^<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/SID419579152 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID23989 |
Total number of triples: 19.