Reducing exposure bias in machine learning training of sequence-to-sequence transducers

US12148419B2 · kind B2 · utility

Assignee

• International Business Machines Corporation · US

Inventors

• Xiaodong Cui · Dongguan, CN
• Brian E. D. Kingsbury · Whitehall Corners, US
• George Andrei Saon · Stamford, US
• David C. Haws · New York, US
• Zoltan Tueske · White Plains, US

Key dates

• Filing date: Dec 13, 2021
• Grant date: Nov 19, 2024
• Expiry date: Oct 28, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/084
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Mechanisms are provided for performing machine learning training of a computer model. A perturbation generator generates a modified training data comprising perturbations injected into original training data, where the perturbations cause a data corruption of the original training data. The modified training data is input into a prediction network of the computer model and processing the modified training data through the prediction network to generate a prediction output. Machine learning training is executed of the prediction network based on the prediction output and the original training data to generate a trained prediction network of a trained computer model. The trained computer model is deployed to an artificial intelligence computing system for performance of an inference operation.