Dell products l.p. (20240135233). METHOD AND SYSTEM FOR MANAGING A FEDERATED COMPUTER VISION REGRESSION MODEL USING DISTRIBUTED TRAINING simplified abstract

METHOD AND SYSTEM FOR MANAGING A FEDERATED COMPUTER VISION REGRESSION MODEL USING DISTRIBUTED TRAINING

Organization Name

dell products l.p.

Inventor(s)

Ian Roche of Glanmire (IE)

Philip Hummel of San Jose CA (US)

Dharmesh M. Patel of Round Rock TX (US)

METHOD AND SYSTEM FOR MANAGING A FEDERATED COMPUTER VISION REGRESSION MODEL USING DISTRIBUTED TRAINING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240135233 titled 'METHOD AND SYSTEM FOR MANAGING A FEDERATED COMPUTER VISION REGRESSION MODEL USING DISTRIBUTED TRAINING

Simplified Explanation

The abstract describes a method for managing hardware resources in computer vision systems by training a federated CV regression model using local hardware resource systems.

• The method involves obtaining a request for a federated CV regression model, performing initial training using an initial dataset, sending training requests to local hardware systems, obtaining local CV regression models, generating the federated model, and distributing it to the local hardware systems.

Potential Applications

This technology could be applied in various industries such as autonomous vehicles, surveillance systems, medical imaging, and robotics for efficient management of computer vision models across multiple hardware systems.

Problems Solved

1. Efficient utilization of hardware resources for training computer vision models. 2. Seamless integration of local hardware systems for federated learning in computer vision applications.

Benefits

1. Improved performance and accuracy of computer vision models. 2. Scalability and flexibility in managing hardware resources for training and deployment of CV models. 3. Cost-effective utilization of local hardware systems for federated learning tasks.

Potential Commercial Applications of this Technology

Optimizing computer vision models for edge devices in IoT applications

Possible Prior Art

Prior art in federated learning techniques for machine learning models in distributed systems could be relevant to this technology.

What are the potential limitations of this technology in real-world applications?

Potential limitations of this technology in real-world applications could include: 1. Compatibility issues with existing hardware systems. 2. Security concerns related to data sharing and model distribution in federated learning setups.

How does this technology compare to traditional methods of managing computer vision models across multiple hardware systems?

This technology offers a more efficient and scalable approach to managing computer vision models across multiple hardware systems compared to traditional methods. By leveraging federated learning techniques, it enables collaborative training of models on local hardware resources while maintaining data privacy and security.

Original Abstract Submitted

a method for managing hardware resources comprises obtaining, by a computer vision (cv) manager, a request for a federated cv regression model, in response to the request: performing an initial training of the federated cv regression model using an initial training dataset to obtain an initial federated cv regression model, sending training requests to two local hardware resource systems, wherein each local hardware resource system implements a local camera system and a processing system, and wherein the training request comprises training a local cv regression model based on the processing system and the local camera system, obtaining the first local cv regression model and the second local cv regression model, generating the federated cv regression model using the two local cv regression models, and distributing the federated cv regression model to the first local hardware resource system and the second local hardware resource system.