Ratna Saripalli, PhD

Dr. Ratna Saripalli, PhD in artificial intelligence and machine learning, is the chief data officer of the Environmental Molecular Sciences Laboratory (EMSL). With over 20 years of technology leadership experience shipping enterprise data platforms and products, Saripalli leads EMSL's high-performance computing and data platform infrastructures. She works closely with platform and software engineers, data architects, computer scientists, and cybersecurity engineers to develop and deliver EMSL's overall digital infrastructure vision and strategy.  
As a technology leader and software engineer, she has industry experience in conceiving, implementing, and managing artificial intelligence, machine learning, data engineering, and analytics products and platforms. Before rejoining Pacific Northwest National Laboratory (PNNL), she served as the vice president of technology at Berkeley Lights, in charge of developing computational methods for large datasets such as gene expression, metabolomics, and proteomics. Before that, she was a senior global director of data science at GE HealthCare for three years, developing world-class artificial intelligence products to revolutionize health care and improve clinical outcomes. She won the GE HealthCare Key Innovator award twice and has contributed to several patents and publications. She served at Microsoft for 11 years in various lead roles, helping ship Bing AdCenter, Office365, and Windows Data Science and Engineering products. Before joining Microsoft, she was a research scientist at PNNL for six years, contributing to global research projects pivotal to genomics and life sciences. 

Research Interests


Scalable, efficient deep reinforcement learning methods for health care and life sciences  
Artificial intelligence/machine learning model compression methods  
High-performance computing and distributed big data management platforms 


Education


MBA, University of California  
PhD in artificial intelligence and machine learning, Colorado State University 
MS in biomedical informatics, Stanford University


Patents


Michael D. Grafham, Kent D. Mitchell, Pei Li, and Venkata Ratnam Saripalli. Attribute Collection and Tenant Selection for Onboarding to a Workload. U.S. Patent US10387212B2, filed 15 June 2017, and issued 20 August 2019. https://patents.google.com/patent/US10387212B2/en. 
Venkata Ratna Saripalli, Gopal Avinash, Min Zhang, Ravi Soni, Jiahui Guan, Dibyajyoti PATI, and Zili Ma. Medical Machine Time-Series Event Data Processor. U.S. Patent US11404145B2, filed 27 November 2019, and issued 02 August 2022. https://patents.google.com/patent/US11404145B2/en. 


Publications

2021
Dong, X., T. Tan, M. Potter, Y.-C. Tsai, G. Kumar, and V. R. Saripalli. 2021. "To raise or not to raise: The autonomous learning rate question." arXiv preprint arXiv:2106.08767. https://doi.org/10.48550/arXiv.2106.08767. 
Dong, X., M. Potter, G. Kumar, Y.-C. Tsai, and V. R. Saripalli. 2021. "Automating Augmentation Through Random Unidimensional Search." arXiv preprint arXiv:2106.08756. https://doi.org/10.48550/arXiv.2106.08756. 
2020
Saripalli, V. R., D. Pati, M. Potter, G. Avinash, and C. W. Anderson. 2020. "Ai-assisted annotator using reinforcement learning." S.N. Computer Science 1 (6): 1–8. https://doi.org/10.48550/arXiv.1910.02052. 
2019
Soni, R., J. Guan, G. Avinash, and V. R. Saripalli. 2019. "HMC: a hybrid reinforcement learning based model compression for healthcare applications." In 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE). Vancouver, BC, Canada, August 22–26, 2019. https://doi.org/10.1109/COASE.2019.8843047. 
Pati, D., C. Favart, P. Bahl, V. Soni, Y.-C. Tsai, M. Potter, J. Guan, X. Dong, and V. R. Saripalli. 2019. "Impact of Inference Accelerators on hardware selection." arXiv preprint arXiv:1910.03060. https://doi.org/10.48550/arXiv.1910.03060. 
Dong, X., J. Hong, H.-M. Chang, M. Potter, A. Chowdhury, P. Bahl, V. Soni, Y.-C. Tsai, R. Tamada, G. Kumar, C. Favart, V. R. Saripalli, G. Avinash. 2019. "FastEstimator: A Deep Learning Library for Fast Prototyping and Productization." arXiv preprint arXiv:1910.04875. https://doi.org/10.48550/arXiv.1910.04875.