US 12,450,896 B2
Apparatus, method, and computer-readable medium for robust response to adversarial perturbations using hyperdimensional vectors
Narayan Srinivasa, San Jose, CA (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Sep. 29, 2023, as Appl. No. 18/478,335.
Application 18/478,335 is a continuation of application No. 17/359,520, filed on Jun. 26, 2021, granted, now 11,854,253.
Prior Publication US 2024/0112460 A1, Apr. 4, 2024
Int. Cl. G06V 20/00 (2022.01); G06F 18/214 (2023.01); G06F 30/34 (2020.01); G06N 3/08 (2023.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G09G 3/20 (2006.01); G09G 3/36 (2006.01)
CPC G06V 20/00 (2022.01) [G06F 18/214 (2023.01); G06F 30/34 (2020.01); G06N 3/08 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G09G 3/2003 (2013.01); G09G 3/3607 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus comprising:
interface circuitry to access a training image;
machine readable instructions; and
at least one programmable circuit to be programmed based on the machine readable instructions to:
determine first hyperdimensional vectors corresponding respectively to patches of the training image;
combine the first hyperdimensional vectors based on second hyperdimensional vectors representative of respective locations of the patches to encode the training image into a third hyperdimensional vector; and
train a neural network based on the third hyperdimensional vector.