US 12,008,478 B2
Systems and methods for training generative models using summary statistics and other constraints
Aaron M. Smith, Corte Madera, CA (US); Anton D. Loukianov, San Mateo, CA (US); Charles K. Fisher, Truckee, CA (US); and Jonathan R. Walsh, El Cerrito, CA (US)
Assigned to Unlearn.AI, Inc., San Francisco, CA (US)
Filed by Unlearn.AI, Inc., San Francisco, CA (US)
Filed on Oct. 19, 2020, as Appl. No. 17/074,364.
Claims priority of provisional application 62/923,337, filed on Oct. 18, 2019.
Prior Publication US 2021/0117842 A1, Apr. 22, 2021
Int. Cl. G06N 20/00 (2019.01); G06F 18/211 (2023.01); G06N 3/088 (2023.01); G06N 7/08 (2006.01)
CPC G06N 3/088 (2013.01) [G06F 18/211 (2023.01); G06N 7/08 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for training a constrained generative model, the method comprising:
receiving a set of data samples from a first distribution;
identifying a set of constraints from a second distribution; and
training a generative model based on the set of data samples and the set of constraints, wherein:
the generative model is a neural network comprising hidden units; and
training the generative model comprises:
training the generative model on the set of data samples;
updating the generative model to add a set of new hidden units and connections to the generative model; and
training the generative model based on the set of constraints by modifying weights for the set of new hidden units.