US 11,854,251 B2
Machine learning-based text recognition system with fine-tuning model
Stefan Iliev Stefanov, New York, NY (US); Boris Nikolaev Daskalov, New York, NY (US); and Akhil Lohchab, New York, NY (US)
Assigned to Hyper Labs, Inc., New York, NY (US)
Filed by Hyper Labs, Inc., New York, NY (US)
Filed on Oct. 20, 2022, as Appl. No. 17/969,817.
Application 17/969,817 is a continuation of application No. 16/744,550, filed on Jan. 16, 2020, granted, now 11,481,691.
Prior Publication US 2023/0050829 A1, Feb. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/20 (2019.01); G06V 10/82 (2022.01); G06F 40/151 (2020.01); G06N 3/08 (2023.01); G06N 5/01 (2023.01); G06V 30/19 (2022.01); G06V 30/40 (2022.01); G06V 30/10 (2022.01)
CPC G06V 10/82 (2022.01) [G06F 40/151 (2020.01); G06N 3/08 (2013.01); G06N 5/01 (2023.01); G06N 20/20 (2019.01); G06V 30/19147 (2022.01); G06V 30/19167 (2022.01); G06V 30/40 (2022.01); G06V 30/10 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
training, at a first compute device remote from a second compute device, a first machine learning model to produce a first trained machine learning model; and
sending all parameters of the first trained machine learning model from the first compute device to the second compute device such that, during operation and after receiving the first trained machine learning model, the second compute device:
(1) trains a second machine learning model based on the first trained machine learning model to produce a second trained machine learning model; and
(2) executes the first trained machine learning model and the second trained machine learning model.