East Lansing, MI, United States of America

Bashir Sadeghi

USPTO Granted Patents = 1 

Average Co-Inventor Count = 3.0

ph-index = 1


Company Filing History:


Years Active: 2025

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Bashir Sadeghi: Innovator in Machine Learning Defense Systems

Introduction

Bashir Sadeghi is a prominent inventor based in East Lansing, MI (US). He has made significant contributions to the field of machine learning, particularly in developing systems that enhance the security of machine learning models against adversarial attacks. His innovative approach has garnered attention in both academic and industrial circles.

Latest Patents

Bashir Sadeghi holds a patent for a "Method and system for creating an ensemble of machine learning models to defend against adversarial examples." This patent describes a system that facilitates the construction of an ensemble of machine learning models. The system determines a training set of data objects, each associated with one of several classes. It divides the training set into multiple partitions and generates a respective machine learning model for each partition using a universal kernel function. The models are trained based on the data objects of the training set, allowing the system to predict outcomes for testing data objects using an ensemble decision rule. He has 1 patent to his name.

Career Highlights

Bashir Sadeghi is currently employed at Xerox Corporation, where he continues to work on innovative solutions in machine learning. His expertise in this area has positioned him as a valuable asset to the company and the broader tech community.

Collaborations

Throughout his career, Bashir has collaborated with notable colleagues, including Alejandro Enrique Brito and Shantanu Rane. These collaborations have further enriched his work and contributed to advancements in the field.

Conclusion

Bashir Sadeghi is a key figure in the development of machine learning defense systems, with a focus on creating robust models that can withstand adversarial challenges. His contributions are paving the way for safer and more reliable machine learning applications.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…