Sharat Chikkerur

Title: Sharat Chikkerur: Innovator in Deep Learning Technologies

Introduction

Sharat Chikkerur is a prominent inventor based in Pittsburgh, PA (US). He has made significant contributions to the field of deep learning and machine learning technologies. With a total of 5 patents to his name, Chikkerur is recognized for his innovative approaches to embedding functions within deep networks.

Latest Patents

One of Chikkerur's latest patents is titled "Using embedding functions with a deep network." This patent outlines methods, systems, and apparatuses, including computer programs encoded on computer storage media, for utilizing embedded functions with a deep network. The method involves receiving an input that comprises a plurality of features, each of a different feature type. Each feature is processed using a respective embedding function to generate numeric values. These embedding functions operate independently, and each is tailored for its respective feature type. The numeric values are then processed using a deep network, which is a machine learning model composed of multiple levels of non-linear operations. Finally, the first alternative representation of the input is processed using a logistic regression classifier to predict a label for the input.

Career Highlights

Chikkerur currently works at Google Inc., where he continues to push the boundaries of technology and innovation. His work focuses on enhancing machine learning models and improving their efficiency and accuracy.

Collaborations

Some of his notable coworkers include Gregory Sean Corrado and Kai Chen, who are also recognized for their contributions to the field of artificial intelligence and machine learning.

Conclusion

Sharat Chikkerur's work in deep learning technologies exemplifies the innovative spirit of modern inventors. His patents and contributions continue to shape the future of machine learning applications.