Thomas Stearns

Title: Thomas Stearns: Innovator in Machine Learning Model Interpretation

Introduction

Thomas Stearns is an accomplished inventor based in Medford, MA (US). He has made significant contributions to the field of machine learning, particularly in the area of model interpretation. His innovative work has garnered attention for its potential to enhance the understanding of machine learning predictions.

Latest Patents

Stearns holds a patent for "Systems and methods for machine learning model interpretation." This patent describes systems and methods for interpreting machine learning model predictions. An example method includes providing a machine learning model configured to receive a plurality of features as input and provide a prediction as output. The plurality of features includes an engineered feature that combines two or more parent features. The method also involves calculating a Shapley value for each feature in the plurality of features and allocating a respective portion of the Shapley value for the engineered feature to each of the two or more parent features. This patent highlights his innovative approach to making machine learning models more interpretable.

Career Highlights

Stearns is currently employed at DataRobot, Inc., where he continues to develop cutting-edge technologies in machine learning. His work at DataRobot has positioned him as a key player in the advancement of AI and machine learning applications.

Collaborations

Throughout his career, Stearns has collaborated with talented individuals such as Mark Benjamin Romanowsky and Jared Bowns. These collaborations have contributed to the success of his projects and the development of innovative solutions in the field.

Conclusion

Thomas Stearns is a notable inventor whose work in machine learning model interpretation is paving the way for more transparent AI systems. His contributions are essential for the future of machine learning and its applications across various industries.