Soumya Ghosh

Title: Soumya Ghosh: Innovator in Federated Learning and Disease Progression Modeling

Introduction

Soumya Ghosh is a prominent inventor based in Boston, MA (US). He has made significant contributions to the fields of machine learning and healthcare through his innovative patents. With a total of 2 patents, Ghosh's work focuses on advancing technology in federated learning and disease progression modeling.

Latest Patents

One of Ghosh's latest patents is titled "Bayesian nonparametric learning of neural networks." This invention addresses the challenges of federated learning, where data is distributed across various servers. The proposed Bayesian nonparametric framework allows for the synthesis of a more expressive global network without the need for data pooling or additional supervision, even with minimal communication. The effectiveness of this invention has been demonstrated through simulations on popular image classification datasets.

Another notable patent is "Identifying and indexing discriminative features for disease progression in observational data." This system facilitates the generation of disease progression models that identify and rank clinical features relevant to different disease stages. The model generation component builds a preliminary model based on observational patient data, while the identification and ranking components enhance the model's accuracy in predicting disease progression.

Career Highlights

Soumya Ghosh is currently employed at International Business Machines Corporation (IBM), where he continues to innovate and contribute to cutting-edge research. His work has garnered attention for its practical applications in healthcare and machine learning.

Collaborations

Ghosh collaborates with talented individuals in his field, including Yu Cheng and Jianying Hu. Their combined expertise fosters an environment of innovation and progress in their respective projects.

Conclusion

Soumya Ghosh is a distinguished inventor whose work in federated learning and disease progression modeling has the potential to transform healthcare technology. His contributions reflect a commitment to advancing knowledge and improving patient outcomes through innovative solutions.