This inventor holds 3 USPTO granted patents. Top assignee: Amazon Technologies, Inc.. Active years: 2024-2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2024-2026
Title: Keerthan Harish Vasist: Innovator in Machine Learning Explanations
Introduction
Keerthan Harish Vasist is a notable inventor based in Sunnyvale, California. He has made significant contributions to the field of machine learning, particularly in the area of model predictions involving text attributes. His innovative approach has garnered attention in the tech industry.
Latest Patents
Keerthan holds a patent titled "Global explanations of machine learning model predictions for input containing text attributes." This patent outlines a method for providing explanatory data sets for predictions generated by machine learning models that handle records with text tokens. The process involves identifying groups of related tokens from text attributes, generating record-level prediction influence scores, and presenting an aggregate prediction influence score for these token groups.
Career Highlights
Currently, Keerthan is employed at Amazon Technologies, Inc., where he continues to develop and refine his expertise in machine learning technologies. His work is instrumental in enhancing the interpretability of machine learning models, which is crucial for various applications in the industry.
Collaborations
Some of his notable coworkers include Cedric Philippe Archambeau and Sanjiv Ranjan Das, who contribute to the collaborative environment at Amazon Technologies, Inc. Their combined efforts foster innovation and drive advancements in machine learning.
Conclusion
Keerthan Harish Vasist is a prominent figure in the realm of machine learning, with a focus on making model predictions more understandable. His contributions through patents and collaboration with talented colleagues highlight his commitment to innovation in technology.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
