US 11,676,034 B2
Initialization of classification layers in neural networks
Emilio Almazán, Alcorcón (ES); Javier Tovar Velasco, Cigales (ES); and Alejandro de la Calle, Valladolid (ES)
Assigned to The Nielsen Company (US), LLC, New York, NY (US)
Filed by The Nielsen Company (US), LLC, New York, NY (US)
Filed on Apr. 28, 2020, as Appl. No. 16/860,947.
Claims priority of provisional application 62/867,757, filed on Jun. 27, 2019.
Prior Publication US 2020/0410320 A1, Dec. 31, 2020
Int. Cl. G06N 3/04 (2023.01); G06N 3/084 (2023.01); G06N 3/08 (2023.01); G06F 17/16 (2006.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/44 (2022.01)
CPC G06N 3/084 (2013.01) [G06F 17/16 (2013.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A tangible computer readable storage medium comprising instructions which, when executed, cause one or more processors to at least:
rank a plurality of classes to be represented by classification vectors based on respective numbers of instances of training data associated with corresponding ones of the classes, the classification vectors to define classification areas in a classification space corresponding to the classes;
initialize the classification vectors to be angled substantially equidistant from each other or to define the classification areas to be substantially equal in size, the classification vectors to span the classification space; and
assign respective ones of the classes to corresponding ones of the classification vectors based on the ranking of the classes.