http://rdf.ncbi.nlm.nih.gov/pubchem/patent/GB-2607153-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_a68790a12228f5b99e176e8aacff640a
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10004
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F30-27
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-0012
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-082
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-063
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F30-27
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00
filingDate 2022-03-03-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_990cab2f1d1ef8494b1fe57a4355df70
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_875330c408444afe9762a82816253e7e
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_dbd7b3fe1a91e733be1ec769fa792575
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_954288ba5d46ea4d2ced361e5d66c0fa
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7fccf58b87c3a2d56a40bea0db6c8f4a
publicationDate 2022-11-30-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber GB-2607153-A
titleOfInvention Selecting a neural network based on an amount of memory
abstract Select a neural network using an amount of memory to be used. In at least one embodiment, a processor includes one or more circuits to cause one or more neural networks (Fig 41A, 4100) to be selected from a plurality of neural networks based, at least in part, on an amount of memory to be used by the one or more neural networks (Fig 41A, 4100). A further embodiment discloses the storage of parameters of the neural networks in memories. Another further embodiment discloses the neural networks to be performing the task of medical image segmentation. The chosen neural networks satisfy a memory constraint 4304, and the network may be chosen using topology search space and cell search space identifications. Connection patterns of neural network layers and their probabilities may be used to perform the searches.
priorityDate 2021-03-03-04:00^^<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/substance/SID419701332
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID423390989
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID11355923
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID22978774

Total number of triples: 32.