http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2010144947-A1
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_8fc0668fd5cbfe23cea7d9bdd5de932a http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_a1d2177ecd72cee4ba8974b932d45a39 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G05B13-027 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 |
| 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/G05B13-00 |
| filingDate | 2010-06-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6bf64ce6b37eca5c504413d3dab6d530 |
| publicationDate | 2010-12-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | WO-2010144947-A1 |
| titleOfInvention | Construction and training of a recurrent neural network |
| abstract | A method for constructing and training a discrete-time recurrent neural network for predicting network inputs is provided. A main recurrent neural network is constructed, formed from a plurality of nodes. Each node hosts a local recurrent neural network formed of a plurality of connected units. The units are connected by weighted connections. A local shadow recurrent neural network is constructed on each node. The local shadow recurrent neural network is a copy of the local recurrent neural network on the respective node, however with certain restrictions on its connection with other nodes. The main recurrent neural network is trained to determine the weights of each connection on each node to provide a local output on each node correlating to a prediction of the local input on the respective node. The training includes, for each discrete time step and on each node: feeding a local input to the local recurrent neural network to cause local network activations; feeding a training input to the local shadow recurrent neural network and applying learning rules to determine connection weights on the local shadow recurrent neural network. The determined connection weights from the local shadow network are copied to the local network. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-10740233-B2 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-9715654-B2 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-9558442-B2 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-9715653-B2 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-9400954-B2 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-106656637-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-106656637-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2018005210-A1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-11628848-B2 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108073986-A |
| priorityDate | 2009-06-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
| Predicate | Subject |
|---|---|
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-2005192915-A1 |
| isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID247820116 |
Total number of triples: 28.