Use of a machine learning model to update another machine learning model
AssigneeQUALCOMM Incorporated
InventorsPirazh Khorramshahi, Upal Mahbub, Adithya Reddy Nallabolu, Gokce Dane, Vikram Gupta
Life of this patent
Estimating the term…
Abstract
A device includes a memory configured to store a first model and a second model. The first model is configured to perform inference based on a first set of parameters corresponding to a first context. The device includes one or more processors configured to process, using the second model, the first set of parameters and input corresponding to a second context to generate an output of the second model. The one or more processors are also configured to update the first model to perform inference using an updated set of parameters based on the output of the second model.
Claims24
A device comprising:
- a memory configured to store a first model and a second model, wherein the first model is configured to perform inference based on a first set of parameters corresponding to a first context, and wherein the second model enables updating the first set of parameters;
- and
- one or more processors configured to:
- process, using the second model, first input corresponding to the first set of parameters and second input corresponding to a second context to generate an output of the second model;
- and
- update the first model to perform inference using an updated set of parameters based on the output of the second model.
A method comprising:
- obtaining a first model and a second model, wherein the first model is configured to perform inference based on a first set of parameters corresponding to a first context, and wherein the second model enables updating the first set of parameters;
- processing, using the second model, first input corresponding to the first set of parameters and second input corresponding to a second context to generate an output of the second model;
- and
- updating the first model to perform inference using an updated set of parameters based on the output of the second model.
A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to:
- obtain a first model and a second model, wherein the first model is configured to perform inference based on a first set of parameters corresponding to a first context, and wherein the second model enables updating the first set of parameters;
- process, using the second model, first input corresponding to the first set of parameters and second input corresponding to a second context to generate an output of the second model;
- and
- update the first model to perform inference using an updated set of parameters based on the output of the second model.
An apparatus comprising:
- means for obtaining a first model and a second model, wherein the first model is configured to perform inference based on a first set of parameters corresponding to a first context, and wherein the second model enables updating the first set of parameters;
- means for processing, using the second model, first input corresponding to the first set of parameters and second input corresponding to a second context to generate an output of the second model;
- and
- means for updating the first model to perform inference using an updated set of parameters based on the output of the second model.
Dependencies are inferred from the claim text.