Naval Bhandari

Title: Naval Bhandari - Innovator in Machine Learning

Introduction

Naval Bhandari is a prominent inventor based in Redmond, WA (US). He has made significant contributions to the field of machine learning, particularly through his innovative patent. His work focuses on enhancing the efficiency and accuracy of multi-class classifiers.

Latest Patents

Naval Bhandari holds a patent for a "System for target-aware machine learning." This invention involves a multi-class classifier (MCC) that is trained using annotated data. The annotated data consists of instances of sample data and their associated label data. The creation of this annotated data, along with the active learning process by the MCC, utilizes various resources. The target-aware active learning system selects sample data for inclusion in an annotation queue based on factors such as the current accuracy of class determination and the priority of that class. As each instance in the sample data is annotated and used for further training, the accuracy of specific classes improves until a predetermined accuracy is achieved. By selectively ordering instances in the annotation queue, the overall resource usage and costs associated with creating annotated data and training are reduced. This approach enhances the overall accuracy for all classes while using a smaller set of annotated data compared to traditional methods.

Career Highlights

Naval Bhandari is currently employed at Amazon Technologies, Inc., where he continues to innovate and contribute to advancements in machine learning technologies. His expertise in this area has positioned him as a valuable asset to his team and the company.

Collaborations

Naval has collaborated with notable colleagues, including Kunal Kotian and Indranil Bhattacharya. These collaborations have further enriched his work and contributed to the development of innovative solutions in the field.

Conclusion

Naval Bhandari's contributions to machine learning through his patent demonstrate his commitment to advancing technology. His work not only improves accuracy and efficiency but also reduces resource usage, showcasing the potential of innovative approaches in the field.