View source for 18063394. METHODS AND SYSTEMS FOR FEDERATED LEARNING UTILIZING CUSTOMER SYNTHETIC DATA MODELS simplified abstract (Capital One Services, LLC)

=METHODS AND SYSTEMS FOR FEDERATED LEARNING UTILIZING CUSTOMER SYNTHETIC DATA MODELS=


==Organization Name==

[[:Category:Capital One Services, LLC|Capital One Services, LLC]]


[[Category:Capital One Services, LLC]]

==Inventor(s)==

[[:Category:Jeremy Goodsitt of Champaign IL (US)|Jeremy Goodsitt of Champaign IL (US)]][[Category:Jeremy Goodsitt of Champaign IL (US)]]

[[:Category:Michael Davis of Arlington VA (US)|Michael Davis of Arlington VA (US)]][[Category:Michael Davis of Arlington VA (US)]]

[[:Category:Taylor Turner of Richmond VA (US)|Taylor Turner of Richmond VA (US)]][[Category:Taylor Turner of Richmond VA (US)]]

[[:Category:Kenny Bean of Herndon VA (US)|Kenny Bean of Herndon VA (US)]][[Category:Kenny Bean of Herndon VA (US)]]

[[:Category:Tyler Farnan of San Diego CA (US)|Tyler Farnan of San Diego CA (US)]][[Category:Tyler Farnan of San Diego CA (US)]]

==METHODS AND SYSTEMS FOR FEDERATED LEARNING UTILIZING CUSTOMER SYNTHETIC DATA MODELS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18063394 titled 'METHODS AND SYSTEMS FOR FEDERATED LEARNING UTILIZING CUSTOMER SYNTHETIC DATA MODELS

Abstract: Methods and systems are described for novel uses and/or improvements to federated learning. As one example, methods and systems are described for improving the applicability of federated learning across various applications and increasing the efficiency of training a global model through federated learning. As another example, methods and systems are described for ensuring comprehensive training data is available to models assigned by the federated learning server. Additionally, methods and systems are described for improving the rate of training a global model through federated learning.

*Simplified Explanation:
The patent application discusses methods and systems for enhancing federated learning by improving applicability, increasing efficiency, ensuring comprehensive training data availability, and enhancing the training rate of global models.

*Key Features and Innovation:
- Improving applicability of federated learning across various applications
- Increasing efficiency of training a global model through federated learning
- Ensuring comprehensive training data availability to models
- Improving the rate of training a global model through federated learning

*Potential Applications:
- Machine learning systems
- Data analytics platforms
- Artificial intelligence applications

*Problems Solved:
- Lack of applicability of federated learning across diverse applications
- Inefficiency in training global models through federated learning
- Inadequate training data availability for models
- Slow training rate of global models

*Benefits:
- Enhanced applicability of federated learning
- Improved efficiency in training global models
- Comprehensive training data availability
- Faster training rate of global models

*Commercial Applications:
Enhancing Federated Learning Efficiency for Machine Learning Systems

*Prior Art:
Prior research on federated learning algorithms and techniques in machine learning and artificial intelligence fields.

*Frequently Updated Research:
Ongoing research on optimizing federated learning algorithms for various applications.

Questions about Federated Learning:
1. How does federated learning improve the efficiency of training global models?
2. What are the potential challenges in ensuring comprehensive training data availability for models in federated learning?


==Original Abstract Submitted==

Methods and systems are described for novel uses and/or improvements to federated learning. As one example, methods and systems are described for improving the applicability of federated learning across various applications and increasing the efficiency of training a global model through federated learning. As another example, methods and systems are described for ensuring comprehensive training data is available to models assigned by the federated learning server. Additionally, methods and systems are described for improving the rate of training a global model through federated learning.



[[Category:G06F21/64]]
[[Category:G06N3/098]]
[[Category:CPC_G06F21/64]]