Indu Thangakrishnan

Title: Indu Thangakrishnan: Innovator in Machine Learning Model Partitioning

Introduction

Indu Thangakrishnan is a prominent inventor based in Santa Clara, CA (US). She has made significant contributions to the field of machine learning, particularly in optimizing the training of models across multiple devices. Her innovative approach has the potential to enhance the efficiency and effectiveness of machine learning applications.

Latest Patents

Indu holds a patent for the "Automatic partitioning of machine learning models for training across multiple devices." This patent describes a method for automatically partitioning a machine learning model to facilitate training across various processing devices. The training job specifies the number of partitions for the model, and an optimization parameter is determined to guide the partitioning process. The method generates a schedule for executing the training job based on the identified partitions, ensuring that the training is executed efficiently.

Career Highlights

Indu Thangakrishnan is currently employed at Amazon Technologies, Inc., where she continues to work on innovative solutions in the realm of machine learning. Her expertise and dedication to advancing technology have made her a valuable asset to her team and the company.

Collaborations

Indu collaborates with talented professionals such as Can Karakus and Rahul Raghavendra Huilgol. These partnerships foster a creative environment that encourages the development of groundbreaking technologies.

Conclusion

Indu Thangakrishnan's contributions to machine learning model partitioning exemplify her innovative spirit and commitment to advancing technology. Her work at Amazon Technologies, Inc. and her patent highlight her role as a leading inventor in the field.