| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_a68790a12228f5b99e176e8aacff640a |
| classificationCPCAdditional |
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/G06T2207-20182 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-0087
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-02
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T9-002
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-002 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T1-40
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-00 |
| filingDate |
2018-07-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_15772e07a3888542e5a566b93ec11a69
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7bc313fbfa0910a481cad1af4b3c90a8
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_40bf7124ff63d85d4d205a00ab6070c0
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_046be4256184fd4a4cab56c7128718a5 |
| publicationDate |
2019-01-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
DE-102018117813-A1 |
| titleOfInvention |
Timely data reconstruction with an external recurrent neural network |
| abstract |
A method, a computer readable medium, and a system are disclosed for temporally stable data reconstruction. A sequence of input data including artifacts is received. A first input data frame is processed using layers of a neural network model to generate an external state comprising a reconstructed first data frame approximating the first input data frame without artifacts. A hidden state generated during processing of the first input data is not provided as an input to the layer to process second input data. The external state is deformed using difference data corresponding to changes between input data frames to produce a deformed external state that is more closely aligned with the second input data frame. The second input data frame is processed based on the deformed external state using the layers of the neural network model to produce a reconstructed second data frame that approximates the second data frame without artifacts. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2023072866-A1 |
| priorityDate |
2017-07-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |