http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2003044829-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_e757fd4fedc4fe825bb81b1b466a0947 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-06 |
filingDate | 2001-07-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7b8c7f4757edc7529b9900667300ab0c http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f395af3ebe62ac1fbf93ac66770abce8 |
publicationDate | 2003-02-14-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | JP-2003044829-A |
titleOfInvention | Method and circuit for associating a norm with each component of an input pattern presented to a neural network |
abstract | (57) [Summary] (with correction) [PROBLEMS] An artificial neural network (AN) based on an input space mapping algorithm during distance evaluation processing N) providing a method and circuit for associating a norm with each component of the input pattern presented in N). A norm set called a "component" norm is stored in a special storage means in the ANN. ANN, It has a global memory that stores all component norms that are common to all neurons of the ANN. For each component of the input pattern, all neurons use the associated component norm during the distance estimation process, using the corresponding prototype component stored in it, to calculate the basic (or partial) distance. Execute The distance basic calculation is then combined using the "distance" norm to determine the final distance between the input pattern and the prototype stored in the neuron. |
priorityDate | 2001-07-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 16.