Search Results - jaideep+vaidya

2 Results

Sort By:

A Method for Secure and Privacy-Preserving Feature Encoding to Enable Federated Data Augmentation and Input Validation

2-step overview of the method Invention Summary: Predictive analytics are essential for optimizing industrial processes, but distributed sensitive data lacks generalizability, suffers from bias, and can't be gathered centrally. Although federated learning and privacy-preserving methods solve data mining problems, they face scalability...

Published: 4/21/2024 | Inventor(s): Jaideep Vaidya, Hafiz Asif, Xinyue Wang, Sitao Min

Keywords(s):

Category(s): Technology Classifications > Artificial Intelligence & Machine Learning, Technology Classifications > Software & Algorithms, Technology Classifications > Software & Copyright

SYNTHETIC DATA GENERATION WHILE PRESERVING OBSERVABLE AND MISSING DATA DISTRIBUTIONS

Model illustrating synthetic data generation Invention Summary: Developers and analysts often require large, accurately labeled datasets when training AI models, though it can be unrealistically time-consuming and expensive, and in many cases impossible due to privacy and confidentiality, to obtain real-world datasets. Algorithms...

Published: 4/25/2024 | Inventor(s): Jaideep Vaidya, Hafiz Asif, Xinyue Wang

Keywords(s):

Category(s): Technology Classifications > Artificial Intelligence & Machine Learning, Technology Classifications > Software & Algorithms, Technology Classifications > Software & Copyright