	US 11,842,262 B2
	Techniques for analyzing vehicle design deviations using deep learning with neural networks
Danil Nagy, New York, NY (US); Daniel Noviello, London (GB); James Stoddart, Atlanta, GA (US); David Benjamin, Brooklyn, NY (US); and Damon Lau, New York, NY (US)
Assigned to AUTODESK, INC., San Francisco, CA (US)
Filed by AUTODESK, INC., San Francisco, CA (US)
Filed on Oct. 11, 2022, as Appl. No. 18/045,809.
Application 18/045,809 is a continuation of application No. 16/362,555, filed on Mar. 22, 2019, granted, now 11,468,292.
Claims priority of provisional application 62/668,731, filed on May 8, 2018.
Prior Publication US 2023/0061993 A1, Mar. 2, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/04 (2023.01); G06N 3/045 (2023.01); G06F 17/15 (2006.01); G06N 3/08 (2023.01); G06F 30/15 (2020.01)

CPC G06N 3/045 (2023.01) [G06F 17/15 (2013.01); G06F 30/15 (2020.01); G06N 3/08 (2013.01)]

24 Claims

1. A computer-implemented method for generating vehicle designs, the method comprising:

encoding, using an encoder network, a first vehicle design into a first location within a latent space representation of vehicle design features;

encoding, using the encoder network, a second vehicle design into a second location within the latent space representation;

generating a first metric based on the first location and the second location, wherein the first metric indicates a degree to which the first vehicle design differs from a characteristic style associated with the second vehicle design;

traversing the latent space representation from the second location towards the first location to a third location in the latent space representation, wherein a distance traversed is determined based on the first metric; and

generating, using a generator network, a third vehicle design based on the third location by increasing a dimensionality associated with the third location to another dimensionality that is greater than or equal to a dimensionality associated with the first vehicle design.