Parameter-efficient neural network model adaptation and inference via matrix sharing
AssigneeAdobe Inc.
InventorsZhao SONG, Ritwik Sinha, Raghavendra Kiran Addanki, Lichen Zhang
Life of this patent
Estimating the term…
Loading patent…
AssigneeAdobe Inc.
InventorsZhao SONG, Ritwik Sinha, Raghavendra Kiran Addanki, Lichen Zhang
Estimating the term…
Some aspects relate to technologies for neural network model adaptation and inference for multiple tasks via matrix sharing. In accordance with some aspects, a neural network model is accessed that has a pre-trained matrix at a layer of the neural network model. A shared matrix and a task matrix are added to the pre-trained matrix at the layer of the neural network model. The neural network model is trained for a plurality of tasks by updating the task matrix for each task to provide a trained task matrix for each task while maintaining the pre-trained matrix and the shared matrix the same for all tasks.
One or more computer storage media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations, the operations comprising:
A computer-implemented method comprising:
A computer system comprising:
Dependencies are inferred from the claim text.