SYSTEMS FOR MULTI-TASK JOINT TRAINING OF NEURAL NETWORKS USING MULTI-LABEL DATASETS
Number of patents in Portfolio can not be more than 2000
United States of America Patent
Stats
-
N/A
Issued Date -
Mar 7, 2024
app pub date -
Sep 2, 2022
filing date -
Sep 2, 2022
priority date (Note) -
Published
status (Latency Note)
Importance
Abstract
Systems and methods for multi-task joint training of a neural network including an encoder module and a multi-headed attention mechanism are provided. In one aspect, the system includes a processor configured to receive input data including a first set of labels and a second set of labels. Using the encoder module, features are extracted from the input data. Using a multi-headed attention mechanism, training loss metrics are computed. A first training loss metric is computed using the extracted features and the first set of labels, and a second training loss metric is computed using the extracted features and the second set of labels. A first mask is applied to filter the first training loss metric, and a second mask is applied to filter the second training loss metric. A final training loss metric is computed based on the filtered first and second training loss metrics.
First Claim
Family
International Classification(s)
- No Non-US Classification to display
Cited Art Landscape
Patent Citation Ranking
- Citation Ranking not provided
Recipient Email Address
Recipient Email Address
Comment
Recipient Email Address
Add to Portfolio(s)
To add this patent to one, or more, of your portfolios, simply click the add button.
This Patent is in these Portfolios:
Add to additional portfolios:
Last Refreshed On:
Changes done successfully