Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Method for training a learning machine having a deep multi-layered network with labeled and unlabeled training data

Method for training a learning machine having a deep multi-layered network with labeled and unlabeled training data

US Patent 8234228 · Granted Jul 31, 2012

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Predicting labels using a deep-learning model2023
Generating representations of speech signals using self-supervised learning2023
Generating a playlist2022
Generating refined object proposals using deep learning models2021
Techniques to predictively respond to user requests using natural language proce2020
End-to-end memory networks2020
Abstractive sentence summarization2020
Generating refined object proposals using deep-learning models2019
Generating object proposals using deep-learning models2019
Generating responses using memory networks2019
Abstractive sentence summarization2019
Identifying entities using a deep-learning model2019