| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ab054d4fd1810c2c2350c52d00de0add |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2201-805
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-063 |
| classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F11-1629
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F11-1497
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F11-1476
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F11-1494
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-063
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-4881 |
| classificationIPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-063 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F11-14
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F11-16 |
| filingDate |
2019-12-19^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_398bb4d0021278b26909ff9a810d3049
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d04fd12b5e6c56464ef6b43b05864775
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e62c92964d74811a2ce046ff7fac3a47
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ed412a76a4ff3f416517a7a87253b968 |
| publicationDate |
2021-06-30^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
GB-2590482-A |
| titleOfInvention |
Fault detection in neural networks |
| abstract |
Method of performing fault detection during neural network computations, the method comprising: scheduling computations onto data processing resources for the execution of a first neural network layer and a second neural network layer, wherein the scheduling includes: for a given one of the layers, scheduling 302 a respective given one of a first computation and a second computation as a non-duplicated computation, in which the given computation is scheduled to be performed only once during the execution of the given neural network layer; and for the other layer, scheduling 304 the respective other computation as a duplicated computation, in which the other computation is scheduled to be performed at least twice during the execution of the other neural network layer to provide a plurality of outputs; performing 306 computations in the data processing resources in accordance with the scheduling; and comparing 308 the outputs from the duplicated computation to selectively provide a fault detection operation during processing of the other neural network layer. Also disclosed is a method of generating a hardware configuration addressing an operational performance target for a data processing system that is programmable to execute neural network layers. |
| priorityDate |
2019-12-19^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |