Bellevue, WA, United States of America

Ke Jiang

USPTO Granted Patents = 1 

Average Co-Inventor Count = 4.0

ph-index = 1


Company Filing History:


Years Active: 2025

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Ke Jiang - Innovator in Machine Learning for Chemical Reactions

Introduction

Ke Jiang is a prominent inventor based in Bellevue, WA (US). He has made significant contributions to the field of machine learning, particularly in the context of chemical reactions. His innovative work has led to the development of a unique system that enhances the retrieval of relevant chemical reaction procedures.

Latest Patents

Ke Jiang holds a patent for a "Machine learning system with two encoder towers for semantic matching." This patent describes a machine learning system that utilizes a contrastive learning-based two-tower model. The model is designed for the retrieval of relevant chemical reaction procedures based on a given query chemical reaction. It employs attention-based transformers and neural networks to convert tokenized representations of chemical reactions into embeddings within a shared embedding space. The architecture of the model includes transformer networks, pooling layers, normalization layers, and neural networks. The training process involves labeled data pairs that consist of a chemical reaction and the corresponding text of a chemical reaction procedure. This innovative model achieves a remarkable average recall at K=5 of 95.9%, demonstrating its high accuracy in semantic matching based on chemical structures.

Career Highlights

Ke Jiang is currently associated with Microsoft Technology Licensing, LLC, where he continues to push the boundaries of machine learning applications. His work is instrumental in advancing the capabilities of retrieval systems in the chemical domain.

Collaborations

Some of his notable coworkers include Sudipto Mukherjee and Liang Du, who contribute to the collaborative environment that fosters innovation and creativity.

Conclusion

Ke Jiang's contributions to machine learning and chemical reactions exemplify the intersection of technology and science. His innovative patent reflects a commitment to enhancing the accuracy and efficiency of chemical procedure retrieval.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…