17949787. RESTRICTED REUSE OF MACHINE LEARNING MODEL DATA FEATURES simplified abstract (AT&T Intellectual Property I, L.P.)
Contents
- 1 RESTRICTED REUSE OF MACHINE LEARNING MODEL DATA FEATURES
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 RESTRICTED REUSE OF MACHINE LEARNING MODEL DATA FEATURES - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.9.1 Unanswered Questions
- 1.9.2 How does the processing system ensure the security and confidentiality of the restricted data features during the model training process?
- 1.9.3 What types of machine learning models can be trained using this processing system, and are there any limitations on the complexity or size of the models that can be handled?
- 1.10 Original Abstract Submitted
RESTRICTED REUSE OF MACHINE LEARNING MODEL DATA FEATURES
Organization Name
AT&T Intellectual Property I, L.P.
Inventor(s)
Prince Paulraj of Coppell TX (US)
Antoine Diffloth of Frisco TX (US)
James Pratt of Round Rock TX (US)
RESTRICTED REUSE OF MACHINE LEARNING MODEL DATA FEATURES - A simplified explanation of the abstract
This abstract first appeared for US patent application 17949787 titled 'RESTRICTED REUSE OF MACHINE LEARNING MODEL DATA FEATURES
Simplified Explanation
The abstract describes a processing system that can train a machine learning model using data features from a second entity that are inaccessible to the first entity making the request.
- The processing system includes at least one processor.
- The system obtains a request from a first entity to train a machine learning model.
- It accesses at least one data feature of a second entity.
- The machine learning model is trained on behalf of the first entity using the data feature of the second entity.
- The trained machine learning model is then provided to the first entity.
Potential Applications
This technology could be applied in industries where sensitive data features need to be used for training machine learning models without exposing them to the requesting entity.
Problems Solved
This system solves the problem of training machine learning models using restricted data features that are not accessible to the entity requesting the model training.
Benefits
The benefits of this technology include enhanced data privacy and security, as sensitive data features are kept confidential while still being utilized for model training.
Potential Commercial Applications
- Secure machine learning model training services
- Data privacy-focused machine learning solutions
Possible Prior Art
There may be existing technologies or methods that focus on data privacy in machine learning model training, but specific prior art is not provided in this context.
Unanswered Questions
How does the processing system ensure the security and confidentiality of the restricted data features during the model training process?
The abstract does not detail the specific mechanisms or protocols used to safeguard the restricted data features during the training of the machine learning model.
What types of machine learning models can be trained using this processing system, and are there any limitations on the complexity or size of the models that can be handled?
The abstract does not specify the range of machine learning models that can be trained using this system, nor does it address any potential limitations on the complexity or size of the models that can be accommodated.
Original Abstract Submitted
A processing system including at least one processor may obtain a request from a first entity to train a machine learning model, access at least one data feature of at least a second entity, and train the machine learning model on behalf of the first entity in accordance with the at least one data feature of the at least the second entity to generate a trained machine learning model, where the at least one data feature of the at least the second entity is a restricted data feature that is inaccessible to the first entity. The processing system may then provide the trained machine learning model to the first entity.
