Time invariant classification

E Hewage, O Armitage… - US Patent …, 2023 - Google Patents
US11610132B2 - Time invariant classification - Google Patents US11610132B2 - Time
invariant classification - Google Patents Time invariant classification Download PDF Info …

Method and system for learning perturbation sets in machine learning

E Wong, J Kolter, WY Lin - US Patent App. 16/930,017, 2022 - Google Patents
METHOD AND SYSTEM FOR LEARNING PERTURBATION SETS IN MACHINE LEARNING
vector in response to the input data and the perturbed version of the input data, decoding the …

Image annotation using one or more neural networks

H Roth, D Yang, D Xu, V Nath - US Patent App. 16/858,219, 2021 - Google Patents
Apparatuses, systems, and techniques are presented to predict annotations for objects in
images. In at least one embodiment, one or more annotations corresponding to one or more …

Adversarial language imitation with constrained exemplars

H Palangi, SK Gabriel, T Hartvigsen, D Ray… - US Patent …, 2024 - Google Patents
Generally discussed herein are devices, systems, and methods for generating a phrase that
is confusing to a language classifier. A method can include determining, by the LC, a first …

Text data protection against automated analysis

NM Tran, K Levacher, B Buesser, M Sinn - US Patent 11,562,139, 2023 - Google Patents
A method, computer system, and a computer program product for text data protection is
provided. The present invention may include receiving a text data. The present invention …

Generating explanations for context aware sequence-to-sequence models

RA Reddy, PK Lohia, SZH Shaikh, D Saha… - US Patent …, 2022 - Google Patents
Methods, systems, and computer program products for gen erating explanations for a
semantic parser are provided herein. A computer-implemented method includes providing to …

Method and apparatus for generating Q and A model by using adversarial learning

DH Kim, WT Jeong, LEE Seanie, G Seong - US Patent 11,710,046, 2023 - Google Patents
A method of generating a question-answer learning model through adversarial learning may
include: sampling a latent variable based on constraints in an input passage; generating an …