Phani Sai Uppu

Title: Phani Sai Uppu - Innovator in Machine Learning and Encryption

Introduction

Phani Sai Uppu is a notable inventor based in Hyderabad, Telangana, India. He has made significant contributions to the field of machine learning, particularly in the context of encryption. His innovative approach addresses the challenges faced in evaluating encrypted machine learning models.

Latest Patents

Phani Sai Uppu holds a patent for a "Method and system for calibrating machine learning models in fully homomorphic encryption applications." This patent presents a technique to evaluate encrypted machine learning models, which conventional methods struggle to address. The system receives an encrypted machine learning model, which can be trained with either encrypted or unencrypted data. It identifies a plurality of evaluation functions using a pattern matching technique and generates approximated functions for each evaluation function. The Expected Calibration Error (ECE) value is then computed based on these approximated functions, allowing for the calibration of the machine learning model. A perfectly calibrated model is indicated by an ECE value of zero.

Career Highlights

Phani Sai Uppu is currently employed at Tata Consultancy Services Limited, where he applies his expertise in machine learning and encryption. His work focuses on developing innovative solutions that enhance the evaluation of encrypted machine learning models.

Collaborations

Phani has collaborated with talented coworkers, including Imtiyazuddin Shaik and Rajan Mindigal Alasingara Bhattachar. Their combined efforts contribute to advancing the field of machine learning and encryption.

Conclusion

Phani Sai Uppu's contributions to the field of machine learning and encryption demonstrate his innovative spirit and dedication to solving complex problems. His patent reflects a significant advancement in evaluating encrypted machine learning models, paving the way for future developments in this critical area.