US 12,230,020 B2
Techniques for dynamic time-based custom model generation
Olaitan Olaleye, Millburn, NJ (US); Arunjeyan T V Seshier Venkatachalapathy, Bengaluru (IN); Jinghou Zhang, Sammamish, WA (US); and Jun Qian, Bellevue, WA (US)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Jan. 27, 2022, as Appl. No. 17/586,583.
Prior Publication US 2023/0237787 A1, Jul. 27, 2023
Int. Cl. G06V 10/82 (2022.01); G06N 3/086 (2023.01); G06V 10/774 (2022.01); G06V 10/778 (2022.01)
CPC G06V 10/82 (2022.01) [G06N 3/086 (2013.01); G06V 10/774 (2022.01); G06V 10/7788 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a computing device, training data, the training data comprising one or more training datasets and an indication of a first time period;
determining, by the computing device and based at least in part on the training data, a modified training dataset and one or more hyperparameter values for a machine learning model, the modified training dataset including a plurality of data objects that are input to the machine learning model to cause training of the machine learning model;
determining, by the computing device and based at least in part on the modified training dataset and the first time period, one or more training iterations, each training iteration of the one or more training iterations corresponding to a second time period and the one or more training iterations corresponding to a total time period that is less than or equal to the first time period;
for each training iteration in the one or more training iterations, training, by the computing device, the machine learning model using the one or more hyperparameter values and the modified training dataset, and the modified training dataset comprising the plurality of data objects in a unique sequence; and
outputting, by a computing device, the trained machine learning model.