US 12,086,719 B2
System and method of machine learning using embedding networks
Lei Chen, Burnaby (CA); Jianhui Chen, Vancouver (CA); Seyed Hossein Hajimirsadeghi, Vancouver (CA); and Gregory Mori, Burnaby (CA)
Assigned to ROYAL BANK OF CANADA, Toronto (CA)
Filed by ROYAL BANK OF CANADA, Toronto (CA)
Filed on Oct. 9, 2020, as Appl. No. 17/067,194.
Claims priority of provisional application 62/914,100, filed on Oct. 11, 2019.
Prior Publication US 2021/0110275 A1, Apr. 15, 2021
Int. Cl. G06N 3/084 (2023.01); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06F 18/2413 (2023.01); G06V 10/74 (2022.01); G06V 10/75 (2022.01); G06V 10/764 (2022.01); G06V 10/772 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)
CPC G06N 3/084 (2013.01) [G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06F 18/24147 (2023.01); G06V 10/751 (2022.01); G06V 10/761 (2022.01); G06V 10/764 (2022.01); G06V 10/765 (2022.01); G06V 10/772 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system for machine learning architecture to generate interpretive data associated with data sets comprising:
a processor;
a memory coupled to the processor and storing processor-executable instructions that, when executed, configure the processor to:
obtain a subject data set;
generate a feature embedding based on the subject data set;
determine an embedding gradient weight based on a prior-trained embedding network and the feature embedding associated with the subject data set, the prior-trained embedding network defined based on a plurality of training embedding gradient weights generated based on a plurality of training samples, each of the plurality of training embedding gradient weights respectively corresponding to a feature map generated from a respective training sample from the plurality of training samples, and wherein the embedding gradient weight is determined based on querying a feature space for the feature embedding associated with the subject data set; and
generate signals for communicating interpretive data associated with the embedding gradient weight.