ALEXANDRIA, Va., July 3 -- United States Patent no. 12,346,810, issued on July 1, was assigned to TATA CONSULTANCY SERVICES Ltd. (Mumbai, India).
"Method and system for self supervised training of deep learning based time series models" was invented by Pradeep Rathore (Pune, India), Arghya Basak (Pune, India), Sri Harsha Nistala (Pune, India) and Venkataramana Runkana (Pune, India).
According to the abstract* released by the U.S. Patent & Trademark Office: "This disclosure relates to method and system for training of deep learning based time-series models based on self-supervised learning. The problem of missing data is taken care of by introducing missing-ness masks. The deep learning model for univariate and multivariate time series dat...