Krishnakumar Subramanian

Title: Innovations of Krishnakumar Subramanian

Introduction

Krishnakumar Subramanian is an accomplished inventor based in Cupertino, California. He has made significant contributions to the field of machine learning and classification models. With a total of two patents to his name, his work focuses on advancing technology in innovative ways.

Latest Patents

Krishnakumar's latest patents include a method for training a classification model using labeled training data that does not overlap with target classifications. This invention involves an online concierge system that trains a classification model as a domain adversarial neural network. The system utilizes training data labeled with source classes from a source domain that do not overlap with target classes from a target domain. The classification model is designed to extract features from images, classify whether an image belongs to the source or target domain, and predict a target class based on the extracted features. A notable aspect of this model is the inclusion of a gradient reversal layer, which helps in extracting domain-invariant features during training.

Career Highlights

Krishnakumar Subramanian is currently employed at Maplebear Inc., where he continues to innovate and develop advanced technologies. His expertise in machine learning and classification systems has positioned him as a valuable asset to his company.

Collaborations

Throughout his career, Krishnakumar has collaborated with talented individuals such as Saurav Manchanda and Haixun Wang. These collaborations have further enriched his work and contributed to the success of his projects.

Conclusion

Krishnakumar Subramanian is a notable inventor whose work in classification models and machine learning is paving the way for future innovations. His contributions to the field are significant and demonstrate his commitment to advancing technology.