Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_e757fd4fedc4fe825bb81b1b466a0947 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F40-20 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-044 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N7-01 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-088 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-006 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate |
2020-02-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d1531d627e94283910840d6735d296d1 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_99563c7a30d8dbefce573ade9ffcd625 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5d3f49935b12737601bfdcbe01d83dd4 |
publicationDate |
2021-09-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-113366510-A |
titleOfInvention |
Perform multi-objective tasks via trained original and dual networks |
abstract |
An example system includes a processor for receiving data for a multi-target task. The processor also performs the multi-objective task on the received data via the trained raw network. The original and dual networks are trained for multi-objective tasks using a Lagrangian loss function representing multi-objectives. The original network is trained to minimize the Lagrangian loss function, and the dual network is trained to maximize the Lagrangian loss function. |
priorityDate |
2019-02-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |