	US 12,073,326 B2
	Joint learning from explicit and inferred labels
Subhabrata Mukherjee, Seattle, WA (US); Guoqing Zheng, Redmond, WA (US); Ahmed Awadalla, Redmond, WA (US); Milad Shokouhi, Seattle, WA (US); Susan Theresa Dumais, Kirkland, WA (US); and Kai Shu, Mesa, AZ (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Oct. 4, 2023, as Appl. No. 18/376,615.
Application 18/376,615 is a division of application No. 16/876,931, filed on May 18, 2020, granted, now 11,816,566.
Prior Publication US 2024/0046087 A1, Feb. 8, 2024
Int. Cl. G06N 3/08 (2023.01); G06N 3/04 (2023.01); G06V 10/82 (2022.01); G06F 16/176 (2019.01)

CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01); G06V 10/82 (2022.01); G06F 16/176 (2019.01)]

20 Claims

1. A system comprising:

a hardware processing unit; and

a storage resource storing computer-readable instructions which, when executed by the hardware processing unit, cause the hardware processing unit to:

receive input data;

process the input data using a machine learning model having an encoding layer to obtain a result, at least the encoding layer having been trained to map first training examples having explicit labels and second training examples having inferred labels into a shared vector space; and

output the result.