Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_82a9e22a923eca64a02a97f0dfb493ed |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-049 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-06 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate |
2014-11-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e442428b35c5d2db7421546317462f85 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_78093be3e0d2a6dc031ae100f188ea9f http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6a6a821d51ff7b7d61702b29f6fa5aaa |
publicationDate |
2015-07-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
TW-201528162-A |
titleOfInvention |
Using replay to perform synaptic learning in a spiking neural network |
abstract |
The various aspects of the present invention relate to methods and apparatus for training an artificial nervous system. Recording the timing of spikes of artificial neurons during training iterations according to certain aspects, during the subsequent training iterations, replaying the spikes of the artificial neurons based on the recorded timing, and based at least in part on the subsequent training Iterative to update the parameters associated with the artificial neuron. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/TW-I673657-B |
priorityDate |
2013-11-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |