http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-101851374-B1
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N99-005 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-082 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate | 2016-09-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2018-04-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2018-04-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | KR-101851374-B1 |
titleOfInvention | Method for learning input data and apparatus using the same |
abstract | According to an aspect of the present invention, there is provided a method of learning input data, comprising the steps of: (a) acquiring the input data by a learning apparatus; and (b) using the neural network having a plurality of layers And learning the input data, wherein among the plurality of layers Consisting of nodes Activation function for the second layer Is characterized by satisfying the following expression, At this time, Lt; Silver The input data for the ith layer and The Th layer, Silver Pre-activation input for the second layer, Activation function By Is calculated The The output data of the second layer +1) th layer, Wow The Lt; th > layer, Is an indicator function, a function that is 1 if the parentheses are true, and 0 otherwise. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2020071618-A1 |
priorityDate | 2016-09-07-04:00^^<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/compound/CID23954 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419557109 |
Total number of triples: 16.