US 12,380,676 B2
Simplifying convolutional neural networks using aggregated representations of images
Vishal Inder Sikka, Los Altos Hills, CA (US); and Kevin Frederick Dunnell, Waltham, MA (US)
Assigned to VIANAI SYSTEMS, INC., Palo Alto, CA (US)
Filed by VIANAI SYSTEMS, INC., Palo Alto, CA (US)
Filed on Jun. 2, 2022, as Appl. No. 17/831,133.
Claims priority of provisional application 63/297,012, filed on Jan. 6, 2022.
Prior Publication US 2023/0215139 A1, Jul. 6, 2023
Int. Cl. G06V 10/764 (2022.01); G06N 3/08 (2023.01); G06V 10/72 (2022.01); G06V 10/74 (2022.01); G06V 10/75 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/764 (2022.01) [G06N 3/08 (2013.01); G06V 10/72 (2022.01); G06V 10/74 (2022.01); G06V 10/751 (2022.01); G06V 10/761 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for simplifying a trained machine learning model, the method comprising:
determining a first set of images associated with a first output class predicted by the trained machine learning model;
generating a first aggregated representation of the first set of images, wherein the first aggregated representation comprises a first plurality of representative pixel values for a plurality of pixel locations included in the first set of images; and
generating a simplified representation of the trained machine learning model that includes a first mapping of the first aggregated representation to the first output class, wherein the first mapping indicates that the trained machine learning model predicts the first output class for one or more input images.